CN107976432B - Heat-resistant steel aging grade measuring method based on support vector machine - Google Patents
Heat-resistant steel aging grade measuring method based on support vector machine Download PDFInfo
- Publication number
- CN107976432B CN107976432B CN201710962614.1A CN201710962614A CN107976432B CN 107976432 B CN107976432 B CN 107976432B CN 201710962614 A CN201710962614 A CN 201710962614A CN 107976432 B CN107976432 B CN 107976432B
- Authority
- CN
- China
- Prior art keywords
- heat
- resistant steel
- support vector
- vector machine
- aging
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/71—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light thermally excited
Landscapes
- Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The invention discloses a method for measuring the aging grade of heat-resistant steel based on a support vector machine, which comprises the following steps: (1) respectively acquiring plasma spectrums of heat-resistant steel samples with different aging grades by using a laser spectrum analysis system in a dot matrix measurement mode; (2) selecting and calculating characteristic intensity variables from the plasma spectral data to form a spectral data matrix; (3) projecting the spectral data matrix to a high-order characteristic space through kernel function conversion; (4) constructing a calibration classification model by using a support vector machine algorithm; (5) and measuring the plasma luminescence spectrum of the heat-resistant steel sample to be measured by using a laser spectrum analysis system, and inputting the spectrum data matrix into the calibration classification model to obtain the aging grade of the sample to be measured. The method has short operation time consumption, and can meet the real-time measurement of industrial fields; the aging grade measuring method has excellent robustness and adaptability to the metallographic inhomogeneity of steel, and the aging grade can be accurately measured without arranging complicated and excessive measuring points on a measuring object.
Description
Technical Field
The invention relates to a field rapid analysis method for the aging grade of heat-resistant steel, in particular to a rapid analysis method for the aging grade of heat-resistant steel based on a laser-induced breakdown spectroscopy combined support vector machine algorithm.
Background
As key large-scale thermal equipment in the industries of electric power, metallurgy, chemical industry, machinery and the like needs to be in service in a high-temperature and high-pressure environment, along with the increase of service time, the metal characteristics of heat-resistant steel parts in the thermal equipment can be changed, ageing and damage gradually occur, cracks and internal injury are generated, the failure and accident probability of the equipment is greatly increased, and the safety and benefit of the whole production link are directly related. The aging grade of the metal is an important index for evaluating the operation of the equipment. Due to the lack of a quick and effective detection technology, the current factory often needs measures such as reducing unit operation parameters, replacing heated parts before due and the like, and the accident incidence rate is reduced by sacrificing economy. Therefore, a new technology for rapidly detecting the aging grade of the heating surface needs to be developed.
According to the standard of the power industry of the people's republic of China, DL/T884-2004, the technical guidance for metal inspection and evaluation of thermal power plants, the aging grade of the heat-resistant steel can be evaluated by comprehensively considering the change of carbides in the crystal interior and the crystal boundary by using the aging evaluation method of the metallographic structure of the non-pearlite steel and the aging structure characteristics of the non-pearlite steel, and can be classified into 1 grade (unaged), 2 grade (slightly aged), 3 grade (moderate aged), 4 grade (completely aged) and 5 grade (severely aged). At present, the state monitoring of high-temperature metal parts at home and abroad is mainly carried out during shutdown maintenance, and the aging grade of the metal parts is evaluated by utilizing technologies such as destructive pipe cutting detection technology, nondestructive detection and the like. The pipe cutting detection mainly comprises the steps of checking chemical components, metallographic structure and damage aging evaluation, normal-temperature and high-temperature short-time mechanical property tests, carbide phase component and phase structure analysis, test of dissimilar welding joints and the like. More detailed status information of the pipe section can be obtained through pipe cutting detection, but damage can be caused to the pipe section, and the status information of the limited pipe section cannot completely represent the use status of other pipe sections. The modern nondestructive detection technology is based on the fact that the structural performance or the use performance of a measured object is not damaged, the characteristics of interaction between sound, light, electricity, heat, magnetism, rays and the like and substances are utilized to detect and measure important parts, detect existing defects of materials and equipment construction, judge the positions, sizes, shapes and types of the existing defects, and evaluate the material performance. The currently adopted nondestructive testing families mainly comprise ray testing and alternating current potential drop method testing. For a high-temperature heating surface, when defects occur, a huge potential safety hazard exists. If the failure tendency, namely the aging grade, of the high-temperature pressure-bearing component can be predicted during production, the component with potential safety hazards can be intensively supervised in a targeted manner so as to avoid major safety accidents. Therefore, the invention provides an on-site rapid analysis method for the aging grade of T91 heat-resistant steel based on a support vector machine and a laser-induced breakdown spectroscopy, so as to meet the requirements.
Disclosure of Invention
Because the traditional high-temperature failure analysis of heat-resistant steel needs to cut the pipe, the nondestructive test can only detect the actual condition of the defect. In order to overcome the defects of the prior art, the invention provides a rapid on-site analysis method for the aging grade of heat-resistant steel based on a support vector machine and laser-induced breakdown spectroscopy. By establishing the relation between the laser plasma spectrum and the change of the metallographic structure of the measured object and building an aging grade detection model, the aging grade of the heat-resistant steel to be measured can be accurately judged.
The specific technical scheme of the invention is as follows:
a method for measuring the aging grade of heat-resistant steel based on a support vector machine comprises the following steps:
(1) firstly, selecting a standard heat-resistant steel sample with 1-5 aging grades, and respectively obtaining plasma spectrums of the heat-resistant steel samples with different aging grades by using a laser spectrum analysis system in a dot matrix measurement mode;
(2) selecting and calculating characteristic intensity variables from the plasma spectral data to form a spectral data matrix;
(3) projecting the spectral data matrix to a high-dimensional characteristic space through kernel function conversion to obtain data distribution characteristics;
(4) constructing a calibration classification model by using a support vector machine algorithm according to the obtained spectral data distribution characteristics;
(5) and measuring the plasma luminescence spectrum of the heat-resistant steel sample to be measured by using a laser spectrum analysis system, and inputting the spectrum data matrix into the calibration classification model to obtain the aging grade of the sample to be measured.
Further, the step (2) specifically comprises:
(21) acquiring n groups of spectral data from the samples of each aging grade;
(22) selecting m spectral intensity variables including spectral line intensity of a matrix element of a representative sample, spectral line intensity of an alloy element of the representative sample, intensity ratio of a spectral line of the alloy element to a spectral line of the matrix element and intensity ratio of an ion line to an atom line from each group of spectral data to form an n multiplied by m dimensional spectral data matrix, namely:
wherein, Xi＝[X1i,X2i,…,Xni]tIs the ith intensity variable;
further, the sample matrix element is Fe.
Further, the sample alloy elements comprise Cr, Mo, Mn and V.
Furthermore, the intensity ratio of the alloy element spectral line to the matrix element spectral line comprises Cr/Fe, Mn/Fe, Mo/Fe and V/Fe.
Further, the strength ratio of the ion line to the atom line comprises FeII/FeI, CrII/CrI and MnII/MnI.
Further, the step (3) utilizes a kernel function to perform nonlinear conversion on the spectrum variable matrix and projects the spectrum variable matrix to a high-dimensional feature space so as to realize feature variable extraction. The characteristic variable extraction is carried out on the laser plasma emission spectra of different samples by utilizing the kernel function conversion, so that the data characteristics in the heat-resistant steel samples with different aging grades can be effectively identified
Further, in the step (3), after the spectral data matrix is projected to the high-dimensional feature space through kernel function conversion, a method for constructing an optimal decision hyperplane is used, that is:
limited by yi(W·Φ(Xi) + b) is more than or equal to 1, i is 1,2, …, n, so as to determine the data distribution characteristics of the heat-resistant steels with different aging grades in a high-dimensional characteristic space.
Further, the step (4) specifically includes:
(41) performing self-scale data preprocessing on the spectral data matrix;
(42) searching for optimal modeling parameters of the support vector machine by using a genetic algorithm;
(43) and establishing an aging grade calibration classification model based on a support vector machine.
Further, the step (5) specifically includes:
(51) continuously striking the surface of the steel by using pulse laser in a portable laser spectrum rapid analysis system for the surface of the heat-resistant steel to be detected, and collecting a generated plasma spectrum by using a spectrometer in the portable laser spectrum rapid analysis system;
(52) inputting the plasma spectrum after self-scale pretreatment into the calibration classification model:
in the formula, λiFor Lagrangian operator, yiModeling a set of intensity variables X in the first stepiCorresponding aging rating label, K (X)iZ) is a kernel function conversion expression;
(53) and (f), (Z) calculating the aging grade of the tested heat-resistant steel to realize the aging grade measurement.
Compared with the prior art, the invention has the following advantages:
1) the invention utilizes the kernel function conversion to extract the characteristic variables of the laser plasma emission spectra of different samples, and can effectively identify the data characteristics of the heat-resistant steel samples with different aging grades.
2) The calibration classification model is established for the characteristic data by using the support vector machine learning method, the robustness and the adaptability to the metallographic inhomogeneity of steel are excellent, and the aging grade of the steel can be accurately measured without arranging complicated and excessive measuring points for a measuring object.
3) The data analysis process of the invention is automatically completed by a computer program, the operation time is short, and the real-time measurement of an industrial field can be satisfied.
4) The pipe cutting and sampling of the heat-resistant steel pipeline to be detected are not needed, and the method has the advantages of being nearly lossless, simple in process, high in accuracy and the like.
Drawings
Fig. 1 is a flowchart of a method for measuring an aging grade of heat-resistant steel based on a support vector machine according to an embodiment of the invention.
FIG. 2 is an exemplary graph of 200-600nm spectral data of an aging grade 1 sample detected in an embodiment of the present invention.
Detailed Description
The following describes the object of the present invention in further detail with reference to the drawings and specific examples, which are not repeated herein, but the embodiments of the present invention are not limited to the following examples.
T91 heat-resistant steel is taken as an example of a detection target.
As shown in fig. 1, a method for measuring the aging grade of heat-resistant steel based on a support vector machine comprises the following steps:
(1) firstly, selecting a standard T91 heat-resistant steel sample with 1-5 aging grades, and respectively obtaining plasma spectrums of the heat-resistant steel samples with different aging grades by a laser spectrum analysis system in a lattice measurement mode;
(2) selecting and calculating characteristic intensity variables from the plasma spectral data to form a spectral data matrix;
(3) performing nonlinear conversion on the spectral data matrix through a kernel function, and then converting and projecting the spectral data matrix to a high-dimensional feature space to obtain data distribution features;
(4) constructing a calibration classification model by using a support vector machine algorithm according to the obtained spectral data distribution characteristics;
(5) and measuring the plasma luminescence spectrum of the heat-resistant steel sample to be measured by using a laser spectrum analysis system, and inputting the spectrum data matrix into the calibration classification model to obtain the aging grade of the sample to be measured.
Specifically, as shown in fig. 1 and 2, the step (2) specifically includes:
(21) obtaining 64 x 30 sets of spectral data as shown in figure 1 from samples of each aging grade;
(22) 63 characteristic spectral line intensities and 120 characteristic spectral line ratios are extracted from each group of data, and 183 variables are extracted. I.e., 1-5 aging grade samples, a 183 x 64 x 30 dimensional matrix of spectral data was obtained. The sample matrix element is Fe. Sample alloying elements included Cr, Mo, Mn, V. The intensity ratio of the alloy element spectral line to the matrix element spectral line comprises Cr/Fe, Mn/Fe, Mo/Fe and V/Fe. The strength ratio of the ion line to the atom line includes FeII/FeI, CrII/CrI, MnII/MnI.
Specifically, in the step (3), after the spectral data matrix is projected to the high-dimensional feature space through kernel function conversion, a method for constructing an optimal decision hyperplane is implemented, that is:
limited by yi(W·Φ(Xi) + b) is more than or equal to 1, i is 1,2, …, n, so as to determine the data distribution characteristics of the heat-resistant steels with different aging grades in a high-dimensional characteristic space.
Specifically, the step (5) specifically includes:
(51) continuously striking the surface of a pipeline by using pulse laser in a portable laser spectrum rapid analysis system for the surface of the heat-resistant steel to be detected to obtain spectral data of an object to be analyzed, and simultaneously collecting a generated plasma spectrum by using a spectrometer in the portable laser spectrum rapid analysis system;
(52) inputting the plasma spectrum after self-scale pretreatment into the calibration classification model:
in the formula, λiFor Lagrangian operator, yiModeling a set of intensity variables X in the first stepiCorresponding aging rating label, K (X)iZ) is a kernel function conversion expression;
(53) and (f), (Z) calculating the aging grade of the tested heat-resistant steel to realize the aging grade measurement.
The above examples of the present invention are merely examples for clearly illustrating the present invention and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. A method for measuring the aging grade of heat-resistant steel based on a support vector machine is characterized by comprising the following steps:
(1) firstly, selecting a standard heat-resistant steel sample with 1-5 aging grades, and respectively obtaining plasma luminescence spectrums of the heat-resistant steel samples with different aging grades by using a laser spectrum analysis system in a lattice measurement mode;
(2) selecting and calculating characteristic intensity variables from the plasma spectral data to form a spectral data matrix;
(3) projecting the spectral data matrix to a high-dimensional characteristic space through kernel function conversion to obtain data distribution characteristics;
(4) constructing a calibration classification model by using a support vector machine algorithm according to the obtained spectral data distribution characteristics;
(5) and measuring the plasma luminescence spectrum of the heat-resistant steel sample to be measured by using a laser spectrum analysis system, and inputting the spectrum data matrix into the calibration classification model to obtain the aging grade of the sample to be measured.
2. The method for measuring the aging grade of the heat-resistant steel based on the support vector machine according to claim 1, characterized in that: the step (2) specifically comprises the following steps:
(21) acquiring n groups of spectral data from the samples of each aging grade;
(22) selecting m spectral intensity variables including spectral line intensity of a matrix element of a representative sample, spectral line intensity of an alloy element of the representative sample, intensity ratio of a spectral line of the alloy element to a spectral line of the matrix element and intensity ratio of an ion line to an atom line from each group of spectral data to form an n multiplied by m dimensional spectral data matrix, namely:
wherein, Xi＝[X1i,X2i,…,Xni]tIs the ith intensity variable;
3. the method for measuring the aging grade of the heat-resistant steel based on the support vector machine according to claim 2, characterized in that: the sample matrix element is Fe.
4. The method for measuring the aging grade of the heat-resistant steel based on the support vector machine according to claim 2, characterized in that: the sample alloy elements comprise Cr, Mo, Mn and V.
5. The method for measuring the aging grade of the heat-resistant steel based on the support vector machine according to claim 2, characterized in that: the intensity ratio of the alloy element spectral line to the matrix element spectral line comprises Cr/Fe, Mn/Fe, Mo/Fe and V/Fe.
6. The method for measuring the aging grade of the heat-resistant steel based on the support vector machine according to claim 2, characterized in that: the strength ratio of the ion line to the atomic line comprises FeII/FeI, CrII/CrI and MnII/MnI.
7. The method for measuring the aging grade of the heat-resistant steel based on the support vector machine according to claim 1, characterized in that: and (3) performing nonlinear conversion on the spectrum variable matrix by using the kernel function, and projecting the spectrum variable matrix to a high-dimensional characteristic space to realize characteristic variable extraction.
8. The method for measuring the aging grade of the heat-resistant steel based on the support vector machine according to claim 1, characterized in that: in the step (3), after the spectral data matrix is projected to the high-dimensional feature space through kernel function conversion, an optimal decision hyperplane is constructed, that is:
limited by yi(W·Φ(Xi) + b) is more than or equal to 1, i is 1,2, …, n, so as to determine the data distribution characteristics of the heat-resistant steels with different aging grades in a high-dimensional characteristic space.
9. The method for measuring the aging grade of the heat-resistant steel based on the support vector machine according to claim 1, characterized in that: the step (4) specifically comprises the following steps:
(41) performing self-scale data preprocessing on the spectral data matrix;
(42) searching for optimal modeling parameters of the support vector machine by using a genetic algorithm;
(43) and establishing an aging grade calibration classification model based on a support vector machine.
10. The method for measuring the aging grade of the heat-resistant steel based on the support vector machine according to claim 1, characterized in that: the step (5) specifically comprises the following steps:
(51) continuously striking the surface of the steel by using pulse laser in a portable laser spectrum rapid analysis system for the surface of the heat-resistant steel to be detected, and collecting a generated plasma spectrum by using a spectrometer in the portable laser spectrum rapid analysis system;
(52) inputting the plasma spectrum after self-scale pretreatment into the calibration classification model:
in the formula, λiFor Lagrangian operator, yiModeling a set of intensity variables X in the first stepiCorresponding aging rating label, K (X)iZ) is a kernel function conversion expression;
(53) and (f), (Z) calculating the aging grade of the tested heat-resistant steel to realize the aging grade measurement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710962614.1A CN107976432B (en) | 2017-10-16 | 2017-10-16 | Heat-resistant steel aging grade measuring method based on support vector machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710962614.1A CN107976432B (en) | 2017-10-16 | 2017-10-16 | Heat-resistant steel aging grade measuring method based on support vector machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107976432A CN107976432A (en) | 2018-05-01 |
| CN107976432B true CN107976432B (en) | 2020-12-22 |
Family
ID=62012452
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710962614.1A Active CN107976432B (en) | 2017-10-16 | 2017-10-16 | Heat-resistant steel aging grade measuring method based on support vector machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107976432B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086547A (en) * | 2018-08-23 | 2018-12-25 | 华南理工大学 | A kind of ageing of metal level measurement method |
| CN109521041B (en) * | 2018-11-30 | 2022-05-17 | 华南理工大学 | XLPE material thermal aging dynamic process multiphase combined detection method |
| CN109741298A (en) * | 2018-12-06 | 2019-05-10 | 东北大学 | Semi-continuous casting alusil alloy microstructure appraisal procedure |
| CN112001446A (en) * | 2020-08-25 | 2020-11-27 | 中国特种设备检测研究院 | Method and device for determining aging grade of high-chromium martensite heat-resistant steel structure |
| CN112816553B (en) * | 2021-01-22 | 2023-04-07 | 国能锅炉压力容器检验有限公司 | Heat-resistant steel aging grade evaluation method based on support vector machine |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200217A (en) * | 2014-08-07 | 2014-12-10 | 哈尔滨工程大学 | Hyperspectrum classification method based on composite kernel function |
| CN106092916A (en) * | 2016-06-05 | 2016-11-09 | 丁旭秋 | Coal mine gas detection method |
| CN106404753A (en) * | 2016-10-18 | 2017-02-15 | 中国大唐集团科学技术研究院有限公司西北分公司 | Classification and verification method of iron ore |
| CN106706599A (en) * | 2016-11-22 | 2017-05-24 | 广东电网有限责任公司电力科学研究院 | Ageing grade analysis method of heated surface of boiler |
| CN106841085A (en) * | 2016-06-05 | 2017-06-13 | 乌鲁木齐职业大学 | Gas measuring method based on KPCA |
| CN106885978A (en) * | 2017-04-20 | 2017-06-23 | 重庆大学 | A kind of paper oil insulation Diagnosis of Aging based on insulating oil Raman spectrum wavelet-packet energy entropy |
-
2017
- 2017-10-16 CN CN201710962614.1A patent/CN107976432B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200217A (en) * | 2014-08-07 | 2014-12-10 | 哈尔滨工程大学 | Hyperspectrum classification method based on composite kernel function |
| CN106092916A (en) * | 2016-06-05 | 2016-11-09 | 丁旭秋 | Coal mine gas detection method |
| CN106841085A (en) * | 2016-06-05 | 2017-06-13 | 乌鲁木齐职业大学 | Gas measuring method based on KPCA |
| CN106404753A (en) * | 2016-10-18 | 2017-02-15 | 中国大唐集团科学技术研究院有限公司西北分公司 | Classification and verification method of iron ore |
| CN106706599A (en) * | 2016-11-22 | 2017-05-24 | 广东电网有限责任公司电力科学研究院 | Ageing grade analysis method of heated surface of boiler |
| CN106885978A (en) * | 2017-04-20 | 2017-06-23 | 重庆大学 | A kind of paper oil insulation Diagnosis of Aging based on insulating oil Raman spectrum wavelet-packet energy entropy |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107976432A (en) | 2018-05-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107976432B (en) | Heat-resistant steel aging grade measuring method based on support vector machine | |
| CN109737309B (en) | Risk source and leakage tracing method and system based on risk identification | |
| CN104697966A (en) | Method for quantitatively analyzing chromium and manganese in steel based on least square support vector machine algorithm combined with laser-induced breakdown spectroscopy | |
| CN103743641B (en) | Method for quickly detecting and evaluating pressure container after fire based on hardness and metallographic phase | |
| Andersson et al. | A historical perspective on Varestraint testing and the importance of testing parameters | |
| CN117233347B (en) | Carbon steel spheroidization grade measuring method, system and equipment | |
| CN103018216A (en) | High-temperature failure tendency rapid analysis method for heated surface of boiler based on LIBS (Laser-induced Breakdown Spectroscopy) | |
| CN106706599A (en) | Ageing grade analysis method of heated surface of boiler | |
| CN109086547A (en) | A kind of ageing of metal level measurement method | |
| CN103278525B (en) | Safety assessment method for pressure-bearing equipment after fire disaster | |
| CN103424397A (en) | Method for detecting nodulizing grade of 12Cr1MoV pearlite on site based on laser plasma spectrum | |
| CN111745320B (en) | Evaluation method and system for improving reliability and applicability of pipeline welding circular seam process | |
| CN115018302A (en) | CB2 steel casting running state supervision and management method | |
| CN108107111A (en) | A kind of heat-resisting steel part nonlinear ultrasonic detection method | |
| Rummel | Nondestructive evaluation–a critical part of structural integrity | |
| CN107123452A (en) | The method of nuclear power station nondestructive evaluation reactor pressure vessel irradiation damage | |
| CN103604913B (en) | Quantitative analysis high-efficiency proofreading method of digital metal element base of metal nondestructive testing | |
| Schmiedt et al. | Influence of condensate corrosion on tensile and fatigue properties of brazed stainless steel joints AISI 304L/BNi‐2 for automotive exhaust systems: Einfluss von Kondensatkorrosion auf die Zug‐und Ermüdungseigenschaften der Edelstahllötverbindungen 1.4307/Ni 620 für Automobilabgassysteme | |
| CN113053471A (en) | Method for nondestructive online detection of Brinell hardness of fan main shaft | |
| Wang et al. | Fatigue crack growth rate data assessment | |
| CN202939128U (en) | Rapid high-temperature failure trend analyzing device for boiler heating surface based on LIBS (Laser-induced Breakdown Spectroscopy) | |
| US9945814B2 (en) | Total integrated tube analysis | |
| Locke¹ | Statistical measurement control | |
| Nihei et al. | Remaining life estimation by fatigue damage sensor | |
| KR101708793B1 (en) | Program for psi/isi monitoring |
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 |