CN114581390B - Particle flow laser detection method, device and storage medium based on plasma image - Google Patents
Particle flow laser detection method, device and storage medium based on plasma image Download PDFInfo
- Publication number
- CN114581390B CN114581390B CN202210181018.0A CN202210181018A CN114581390B CN 114581390 B CN114581390 B CN 114581390B CN 202210181018 A CN202210181018 A CN 202210181018A CN 114581390 B CN114581390 B CN 114581390B
- Authority
- CN
- China
- Prior art keywords
- spectrum data
- particle flow
- particle
- plasma
- laser
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000002245 particle Substances 0.000 title claims abstract description 88
- 238000001514 detection method Methods 0.000 title claims abstract description 34
- 238000003860 storage Methods 0.000 title claims abstract description 8
- 238000001228 spectrum Methods 0.000 claims abstract description 69
- 238000000034 method Methods 0.000 claims abstract description 41
- 238000012360 testing method Methods 0.000 claims description 11
- 238000004445 quantitative analysis Methods 0.000 claims description 9
- 230000015556 catabolic process Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000000695 excitation spectrum Methods 0.000 claims description 4
- 238000002790 cross-validation Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000002536 laser-induced breakdown spectroscopy Methods 0.000 abstract description 8
- 238000004458 analytical method Methods 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 abstract description 7
- 239000000126 substance Substances 0.000 abstract description 6
- 230000008569 process Effects 0.000 abstract description 5
- 230000003993 interaction Effects 0.000 abstract description 4
- 239000007787 solid Substances 0.000 abstract description 3
- 230000003595 spectral effect Effects 0.000 description 11
- 239000003245 coal Substances 0.000 description 9
- 230000005284 excitation Effects 0.000 description 6
- 230000008878 coupling Effects 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 4
- 238000005859 coupling reaction Methods 0.000 description 4
- 230000001808 coupling effect Effects 0.000 description 3
- 238000002679 ablation Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000004611 spectroscopical analysis Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000295 emission spectrum Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 239000008187 granular material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The invention discloses a particle flow laser detection method, equipment and a storage medium based on a plasma image, which comprise the steps of obtaining an effective spectrum data set, and constructing a particle flow characteristic calibration model based on a partial least square method, obtaining effective spectrum data of a particle sample to be detected, inputting the particle flow characteristic calibration model, and detecting the characteristics of the sample to be detected. The invention utilizes the plasma image information visually expressing the interaction of laser and the substance to be tested to remove the spectrum data influenced by the unstable fluctuation of the particle flow, optimizes the spectrum data identification process and improves the solid particle flow characteristic analysis performance based on the laser-induced breakdown spectroscopy technology.
Description
Technical Field
The invention relates to a particle flow state substance characteristic analysis method, in particular to a particle flow laser detection method, device and storage medium based on a plasma image.
Background
The granular fluid substances widely exist in the nature and industrial processes, and the method for researching and acquiring the characteristics of the granular materials is convenient and efficient, and has practical significance for optimizing the operation of the industrial process and improving the benefit.
The traditional particle material characteristic detection often needs to carry out processes such as sampling, off-line sample preparation and the like, has the defects of long analysis time, poor real-time performance and the like, and is difficult to meet the real-time/on-line automatic control requirement in industrial production. The laser-induced breakdown spectroscopy technology has the advantages of remote, real-time, rapid and multi-element synchronous detection and the like, and has been applied to the characteristic analysis and measurement of particle flow state materials. The particle flow is easy to cause unstable interaction of laser-substance due to the non-uniformity of particle size and flow, vibration of equipment or fluctuation of environment, and the like, and the coupling effect of the laser-substance is affected. The validity of the data obtained by the interaction of different pulse lasers and particle streams needs to be judged and screened. The existing methods include the following: 1. judging the effectiveness of data according to the intensity value of an excitation spectral line or the signal-to-noise ratio of main characteristic elements of a sample to be detected in the obtained spectrum; 2. a spectrum characteristic peak standard deviation method, 3, judging by a normal curve method based on characteristic spectral line intensity; 4. spectral characteristic peak step-degree method. The identification methods are all based on the obtained plasma spectrum information to perform laser sample coupling state analysis, are easily influenced by a light receiving instrument, light path setting, sample characteristics and environmental changes, and have certain limitations.
Disclosure of Invention
In order to overcome the defects and shortcomings in the prior art, the invention provides a particle flow laser detection method, equipment and a storage medium based on a plasma image.
According to the invention, the laser-induced breakdown spectroscopy detection system is utilized to obtain particle flow spectroscopy data, meanwhile, a CCD camera is adopted to directly observe the coupling states of different laser pulses and particle flow, the accurate elimination of invalid spectroscopy data is realized based on camera images, and the detection performance of the laser-induced breakdown spectroscopy technology on the solid particle flow characteristics is optimized.
The invention adopts the following technical scheme:
a particle flow laser detection method based on plasma images, comprising:
Obtaining effective spectrum data sets of a plurality of particle flow samples with known characteristic indexes, and constructing a particle flow characteristic scaling model based on a partial least square method;
and obtaining effective spectrum data of the particle sample to be detected, inputting the effective spectrum data into a particle flow characteristic calibration model, and detecting the characteristics of the particle sample to be detected.
Further, the effective spectrum data sets of the particle flow samples with known characteristic indexes are obtained, and a particle flow characteristic scaling model based on a partial least square method is constructed, specifically:
obtaining a plurality of laser-induced plasma spectrum data of a plurality of particle flow samples with known characteristic indexes by using a laser-induced breakdown spectrum detection system, and acquiring laser-induced plasma images corresponding to the spectrum data by using a CCD camera;
Obtaining a plasma image area;
Taking an average value of areas of a plasma region corresponding to a plurality of typical effective excitation spectrums as an initial threshold value, setting different area threshold values according to a certain incremental gradient, and deleting corresponding spectrum data of which the plasma image area is smaller than the area threshold value to obtain effective spectrum data;
obtaining an optimal area threshold value by adopting a partial least square method for the effective spectrum data;
and establishing a particle flow characteristic calibration model by utilizing the effective spectrum data of a plurality of particle flow samples with known characteristic indexes.
Further, the method for obtaining the optimal area threshold value by adopting the partial least square method for the effective spectrum data comprises the following specific steps:
And taking an average value of areas of the plasma region corresponding to a plurality of typical effective excitation spectrums as an initial threshold value, setting different area thresholds according to a certain incremental gradient, obtaining effective spectrum data of different particle samples, and checking the data for establishing the robustness of the model by adopting a partial least square ten-fold cross-validation method for the plurality of effective spectrum data.
Further, the method for verifying the robustness of the data for establishing the model by using a partial least square ten-fold cross verification method is specifically as follows: the spectrum data are randomly distributed into a training set and a testing set according to the sample types and the proportion, partial least square modeling is carried out by utilizing the training set data, the established model is used for quantitative analysis of the testing set, and the average value of the quantitative analysis accuracy of the multiple testing sets is used as the preferable discrimination standard of the area threshold.
Further, a plasma image area is obtained, specifically:
and determining a brightness threshold value which can be judged as the plasma region according to the background of the plasma image and the brightness value of the plasma region, and counting pixels with the brightness value larger than the threshold value in the image to obtain the plasma area.
Further, obtaining effective spectrum data of a particle sample to be detected, inputting a particle flow characteristic calibration model, and detecting characteristics of the sample to be detected, wherein the method specifically comprises the following steps:
A laser-induced breakdown spectrum detection system and a CCD camera are utilized to obtain a plasma image of a particle sample to be detected, and effective spectrum data after the optimal screening area is obtained;
And inputting the effective spectrum data to establish a particle flow characteristic calibration model to realize the detection of the characteristics of the sample to be detected.
Further, the luminance threshold value is an average value of luminance within the image background setting area.
Further, 600 spectra and plasma image data were acquired for each sample.
An apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the particle stream excitation detection method when executing the program.
A storage medium having stored thereon a computer program which when executed by a processor implements the particle stream excitation detection method.
The invention has the beneficial effects that:
according to the invention, by combining a plasma image technology and a laser-induced breakdown spectroscopy technology, the laser-particle flow coupling effect is observed through a CCD camera, the accuracy and the effectiveness of removing invalid spectrums are improved based on a plasma image, and the application of the invention improves the detection performance of the laser-induced breakdown spectroscopy technology applied to particle flow samples.
Drawings
FIG. 1 is a schematic flow chart of the present invention;
Fig. 2 is a graphical representation of plasma versus spectrum for effective breakdown, partial breakdown, and ineffective breakdown in an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but embodiments of the present invention are not limited thereto.
Example 1
As shown in fig. 1, a particle flow laser detection method based on a plasma image includes the following steps:
step one, optimizing an image screening method threshold value and modeling and scaling, wherein the method comprises the following steps:
Placing a particle sample (taking coal as an example) with known characteristics into a particle flow laser induced breakdown spectroscopy detection system, enabling the sample to flow in a particle flow state through a gas circuit system, simulating an actual industrial production process, exciting the particle flow by using pulse laser to generate plasma, collecting a plasma emission spectrum through a spectrometer, simultaneously acquiring coupling effects of each pulse laser and the particle flow, namely a plasma image, by using a CCD camera, and acquiring 600 spectra and image data of each sample.
As shown in fig. 2, the effective coupling of the laser and the particle flow can generate a plasma with larger volume and symmetry, the collected characteristic spectrum can also detect the characteristic spectral line of the main element of the fire coal, and the partial and ineffective coupling of the laser is caused by the factors such as fluctuation of the particle flow, and the partial effective ablation quality is less, so that the characteristic spectral line of the main element of the fire coal in the plasma generated by the lower effective ablation quality is weaker or can not be detected. The plasma area in the plasma image is chosen as a basis for identifying the spectral effectiveness.
And analyzing the brightness difference between the background and the plasma region in the plasma image, taking the brightness average value of a certain region range of the image background as the brightness value of the background, calculating to obtain 1500, namely, recognizing that the brightness value of the image pixel is larger than the brightness value of the image pixel as the excited plasma region, counting the number of pixel points in the image, and further calculating to obtain the area of the plasma region.
Specifically, the area in the present embodiment ranges from 30×30 pixel points.
And taking an average value of areas of the plasma areas corresponding to a plurality of typical effective excitation spectrums as an initial threshold value, setting different plasma area threshold values according to a certain incremental gradient, and rejecting spectrum data of which the areas of the plasma areas are smaller than the threshold value to obtain effective spectrum data.
A partial least squares ten fold cross validation method is employed on the valid spectral data to verify the robustness of the data for modeling.
Further, spectral data was randomly assigned to training and testing sets at a 9:1 ratio by sample class. And modeling by using the training set data by using a partial least square method.
Taking typical characteristic indexes of fire coal as an example, the specific process adopting the method comprises the following steps:
Taking the volatile content of typical characteristic indexes of the fire coal as verification reference, modeling the spectrum by using a partial least square method, and establishing a relation between characteristic indexes and the spectrum: y=k 0+k1x1″+k1x2″+...knxn ", where k o,k1,k2,.....kn is the coefficient resulting from the partial least squares iteration.
The established model was used for quantitative analysis of volatile content of test set samples. The modeling and analysis processes are carried out 10 times, and the average value of quantitative analysis accuracy of a 10-time test set is used as a preferable discrimination standard of the area threshold value to determine the optimal area threshold value. When the threshold is 4000, the cross-validated correlation coefficient (R 2 =0.940) reaches a maximum value, at which point the root mean square error (rmse= 1.830) reaches a minimum value, so the optimal screening threshold is 4000. Screening the spectrum data based on the threshold value to obtain an effective spectrum data set.
Under the same test condition, the spectrum data processed by the image method is reduced by 10-15% compared with the characteristic spectral line intensity fluctuation (RSD) of the main element of the fire coal in the original spectrum data without spectral elimination.
Step two, particle flow characteristic detection, comprising the following steps:
And (3) carrying out laser detection and plasma image acquisition on the particle coal sample to be detected, and carrying out spectrum screening by adopting an optimal area threshold value, wherein the optimal area threshold value is obtained in the step one, and the embodiment is 4000.
Taking the characteristic volatile matters of the fire coal as examples, substituting the characteristic volatile matters into the modeling type in the first step to realize quantitative analysis of the index.
Table 1 shows that the image method has the best quantitative analysis and optimization effects on the volatile matters of the pulverized coal particles by comparing the image method with the optimized results of the final quantitative analysis by the existing standard deviation method and signal-to-noise ratio method and taking the correlation coefficient (R 2), the Root Mean Square Error (RMSE) and the Average Absolute Error (AAE) of the test set as evaluation indexes.
TABLE 1
The invention utilizes the plasma image information visually expressing the interaction of laser and the substance to be tested to remove the spectrum data influenced by the unstable fluctuation of the particle flow, optimizes the spectrum data identification process and improves the solid particle flow characteristic analysis performance based on the laser-induced breakdown spectroscopy technology.
Example 2
An apparatus comprising a memory, a processor and a computer program stored on the memory and operable on the processor, the processor implementing the particle flow excitation detection method when executing the program, specifically comprising obtaining valid spectral datasets of a plurality of particle flow samples of known characteristic indicators, constructing a partial least squares based particle flow characteristic scaling model;
and obtaining effective spectrum data of the particle sample to be detected, inputting the effective spectrum data into a particle flow characteristic calibration model, and detecting the characteristics of the particle sample to be detected.
Example 3
A storage medium having stored thereon a computer program which when executed by a processor implements the particle stream excitation detection method.
The particle flow excitation detection method comprises the steps of obtaining effective spectrum data sets of a plurality of particle flow samples with known characteristic indexes, and constructing a particle flow characteristic scaling model based on a partial least square method;
and obtaining effective spectrum data of the particle sample to be detected, inputting the effective spectrum data into a particle flow characteristic calibration model, and detecting the characteristics of the particle sample to be detected.
The embodiments described above are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the embodiments described above, and any other changes, modifications, substitutions, combinations, and simplifications that do not depart from the spirit and principles of the present invention should be made in the equivalent manner, and are included in the scope of the present invention.
Claims (6)
1. A particle flow laser detection method based on a plasma image, comprising the steps of:
Obtaining effective spectrum data sets of a plurality of particle flow samples with known characteristic indexes, and constructing a particle flow characteristic scaling model based on a partial least square method;
Obtaining effective spectrum data of a particle sample to be detected, inputting the effective spectrum data into a particle flow characteristic calibration model, and detecting the characteristics of the particle sample to be detected;
the effective spectrum data set of a plurality of particle flow samples for obtaining known characteristic indexes is used for constructing a particle flow characteristic scaling model based on a partial least square method, and the method specifically comprises the following steps:
obtaining a plurality of laser-induced plasma spectrum data of a plurality of particle flow samples with known characteristic indexes by using a laser-induced breakdown spectrum detection system, and acquiring laser-induced plasma images corresponding to the spectrum data by using a CCD camera;
Obtaining a plasma image area;
Deleting the corresponding spectrum data of which the plasma image area is smaller than the area threshold value to obtain effective spectrum data;
obtaining an optimal area threshold value by adopting a partial least square method for the effective spectrum data;
Establishing a particle flow characteristic calibration model by utilizing effective spectrum data of a plurality of particle flow samples with known characteristic indexes;
the optimal area threshold value is obtained by adopting a partial least square method on the effective spectrum data, and specifically comprises the following steps:
Taking an average value of areas of plasma areas corresponding to a plurality of typical effective excitation spectrums as an initial threshold value, setting different area thresholds according to an incremental gradient set by a user, obtaining effective spectrum data of different particle samples, and checking the data for establishing the robustness of a model by adopting a partial least square ten-fold cross validation method on the plurality of effective spectrum data;
The method for verifying the robustness of the data for establishing the model by adopting a partial least square ten-fold cross verification method on a plurality of effective spectrum data comprises the following steps: the spectrum data are randomly distributed into a training set and a testing set according to the sample type and the proportion, partial least square modeling is carried out by utilizing the training set data, the established model is used for quantitative analysis of the testing set, and the average value of the quantitative analysis accuracy of the multiple testing sets is used as the preferable discrimination standard of the area threshold;
the plasma image area is obtained, specifically:
And determining a brightness threshold value of the plasma region according to the background of the plasma image and the brightness value of the plasma region, and counting pixel points with the brightness value larger than the threshold value in the image to obtain the plasma image area.
2. The particle flow laser detection method according to claim 1, wherein effective spectrum data of a particle sample to be detected is obtained, and the effective spectrum data is input into a particle flow characteristic calibration model to realize detection of characteristics of the particle sample to be detected, specifically:
A laser-induced breakdown spectrum detection system and a CCD camera are utilized to obtain a plasma image of a particle sample to be detected, and effective spectrum data after the optimal screening area is obtained;
And inputting the effective spectrum data to establish a particle flow characteristic calibration model to realize the detection of the characteristics of the sample to be detected.
3. The particle flow laser detection method of claim 1, wherein the brightness threshold is an average of brightness over a set area of the image background.
4. The particle flow laser detection method of claim 1, wherein 600 spectra and plasma image data are collected for each sample.
5. A particle flow laser detection apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the particle flow laser detection method of any one of claims 1-4 when the program is executed by the processor.
6. A storage medium having stored thereon a computer program which, when executed by a processor, implements the particle stream laser detection method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210181018.0A CN114581390B (en) | 2022-02-25 | 2022-02-25 | Particle flow laser detection method, device and storage medium based on plasma image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210181018.0A CN114581390B (en) | 2022-02-25 | 2022-02-25 | Particle flow laser detection method, device and storage medium based on plasma image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114581390A CN114581390A (en) | 2022-06-03 |
| CN114581390B true CN114581390B (en) | 2024-08-30 |
Family
ID=81773116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210181018.0A Active CN114581390B (en) | 2022-02-25 | 2022-02-25 | Particle flow laser detection method, device and storage medium based on plasma image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114581390B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105784678A (en) * | 2016-01-31 | 2016-07-20 | 华南理工大学 | Method for identifying laser plasma spectrum of grain flow through standard deviation of characteristic peak strength |
| CN112255149A (en) * | 2020-10-10 | 2021-01-22 | 中国科学院近代物理研究所 | Method and system for detecting particle size of loose particle accumulation and storage medium |
-
2022
- 2022-02-25 CN CN202210181018.0A patent/CN114581390B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105784678A (en) * | 2016-01-31 | 2016-07-20 | 华南理工大学 | Method for identifying laser plasma spectrum of grain flow through standard deviation of characteristic peak strength |
| CN112255149A (en) * | 2020-10-10 | 2021-01-22 | 中国科学院近代物理研究所 | Method and system for detecting particle size of loose particle accumulation and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114581390A (en) | 2022-06-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110261405B (en) | Insulator pollution component identification method based on microscopic hyperspectral technology | |
| CN109799195B (en) | High-precision quantitative analysis method for laser-induced breakdown spectroscopy | |
| US6424151B2 (en) | Method and apparatus for evaluation of eddy current testing signal | |
| WO2012156667A1 (en) | Spectroscopic apparatus and methods for determining components present in a sample | |
| CN103134850A (en) | Tea quality rapid detection apparatus and detection method based on characteristic fragrance | |
| CN108181266B (en) | TD L AS gas concentration detection method | |
| CN116030310A (en) | Sample classification method and system based on laser-induced breakdown spectroscopy technology | |
| CN112782151B (en) | Data processing method for improving classification accuracy of laser-induced breakdown spectroscopy | |
| CN104730043A (en) | Method for measuring heavy metals in ink based on partial least squares | |
| CN111879709A (en) | Method and device for detecting spectral reflectivity of lake water body | |
| CN105956591B (en) | A kind of online hot parts infrared image spectrum sampling Detection method | |
| CN114581390B (en) | Particle flow laser detection method, device and storage medium based on plasma image | |
| CN105223140A (en) | The method for quickly identifying of homology material | |
| CN106528665A (en) | AOI equipment test file searching method and system | |
| CN102103079B (en) | Spectrum analysis method | |
| CN117269109B (en) | Method for detecting chloride ion content in concrete structure based on near infrared spectrum | |
| CN116380875A (en) | Novel method for quickly establishing quantitative prediction model of coal components based on small sample size | |
| CN109709060B (en) | Method for measuring asphalt softening point, penetration degree and mass loss | |
| CN111044504B (en) | Coal quality analysis method considering uncertainty of laser-induced breakdown spectroscopy | |
| CN117310068A (en) | Ion chromatograph fault diagnosis analysis system and method thereof | |
| CN114970164A (en) | Refined steel classification quantitative method and portable system | |
| CN113219042A (en) | Device and method for analyzing and detecting components in human body exhaled air | |
| CN113324921A (en) | Construction method and application of astragalus seed chlorophyll content determination model | |
| CN115326775B (en) | Fluorescence detection method and system fused with intrinsic priori knowledge | |
| CN112508862A (en) | Method for enhancing magneto-optical image of crack by improving GAN |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |