CN114580274A - Titanium alloy stress corrosion critical stress intensity factor prediction method - Google Patents

Titanium alloy stress corrosion critical stress intensity factor prediction method Download PDF

Info

Publication number
CN114580274A
CN114580274A CN202210158920.0A CN202210158920A CN114580274A CN 114580274 A CN114580274 A CN 114580274A CN 202210158920 A CN202210158920 A CN 202210158920A CN 114580274 A CN114580274 A CN 114580274A
Authority
CN
China
Prior art keywords
iscc
titanium alloy
regression model
predicting
intensity factor
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.)
Pending
Application number
CN202210158920.0A
Other languages
Chinese (zh)
Inventor
张卫冬
张琬滢
艾轶博
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Science and Technology Beijing USTB
Original Assignee
University of Science and Technology Beijing USTB
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of Science and Technology Beijing USTB filed Critical University of Science and Technology Beijing USTB
Priority to CN202210158920.0A priority Critical patent/CN114580274A/en
Publication of CN114580274A publication Critical patent/CN114580274A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)

Abstract

The invention provides a prediction method of a titanium alloy stress corrosion critical stress intensity factor, and belongs to the technical field of titanium alloy corrosion detection. The method comprises the following steps: acquiring a training sample set and a test sample set; inputting a training sample set into multiple different regression models for training, inputting a test sample set into the trained regression models for testing after training is finished, and obtaining K of each regression model according to a test resultISCCThe prediction accuracy of the predicted value; inputting the tissue structure, loading direction, pressure, temperature and dissolved oxygen concentration of the titanium alloy to be predicted under the condition into a regression model with the highest prediction accuracy, and outputting KISCCAnd (6) predicting the value. By adopting the method, the microstructure, the loading direction, the pressure, the temperature and the solution of the titanium alloy to be predicted under the condition can be utilizedFive parameters of oxygen concentration are solved to accurately predict the critical stress intensity factor K of stress corrosionISCC。

Description

Titanium alloy stress corrosion critical stress intensity factor prediction method
Technical Field
The invention relates to the technical field of titanium alloy corrosion detection, in particular to a method for predicting a critical stress intensity factor of titanium alloy stress corrosion.
Background
The titanium alloy corrosion evaluation under the deep and open sea environment is a systematic engineering, and relates to complex scientific and technical problems of evolution behavior of materials under service conditions in a multi-factor coupling environment, scale association from microcosmic to real structures and the like. The material corrosion data is the basis for researching the corrosion failure rule of the material and the performance evolution of the material. In recent years, with the rapid development of data-driven modeling ideas, the development of a new generation of artificial intelligence technology represented by machine learning provides a new idea for material failure rule mining, material corrosion rate prediction and failure boundary early warning in a deep and open sea environment. Due to a plurality of factors influencing the corrosion of the deep and far sea titanium alloy, the action rule is relatively complex, high nonlinearity exists, and the black box property of the deep learning model enables the deep learning model to have very limited action in the research of the corrosion rule of the deep and far sea material.
Stress corrosion refers to the process of material failure in which the metal is subjected to a combination of strain and corrosion caused by residual or applied stress in the corrosive medium. This corrosion generally penetrates the grains, so-called transgranular corrosion, while there are instances of intergranular corrosion already. When stress corrosion occurs in a metal, cracks occur only in a local region from the outside to the inside. While the crack propagates in the trunk, several branches develop simultaneously. The crack is macroscopically vertical to the direction of tensile stress, the microscopic fracture mechanism is generally fracture along crystal, and also can be transgranular cleavage fracture or the mixture of the two, and the fracture surface can see 'mud-shaped pattern' corrosion products and corrosion pits. The stress corrosion generally belongs to brittle fracture and comprises three parts, namely an inoculation area, an expansion area and an instantaneous fracture area. For crack propagation rates, stress corrosion presents a critical stress intensity factor KISCCI.e. the actual value of the critical stress intensity factor is greater than KISCCThe crack will propagate. The crack propagation rate of stress corrosion is generally 10-6～10-3mm/min. Stress intensity factor (K) for stress corrosion crack propagation under stress corrosion conditionsⅠ) Has a lower threshold value of KISCC. If KⅠValue less than KISCCThe crack propagation of the stress corrosion does not occur. KISCCDepending on the medium and the material, it is experimentally determined and is also related to the temperature of the medium. Plane strain fracture toughness is an index of fracture toughness of a material expressed as KICThe condition for plane strain fracture is that the crack tip plastic zone size is much smaller than the crack length and other geometric dimensions. General KISCC＝(0.2～0.5)KIC. In a system where stress corrosion is likely to occur, K is calculated if the size of existing cracks can be effectively detectedⅠ<KISCCThe structure is safe. If KⅠ>KISCCBut less than KICAt this time, the crack will be subjected to stress corrosion propagation, and the safe service life needs to be predicted. Reducing the working stress of the component, eliminating various residual stresses in the component by heat treatment, or trying to reduce the temperature differential stress are all effective measures to avoid and slow down stress corrosion.
The titanium alloy corrosion basic data in the deep and open sea environment are less in accumulation but more in data source, and strong heterogeneity exists among multi-source experimental data, so that the data can be classified into sparse multi-source heterogeneous characteristics, on one hand, missing values in the experimental data are required to be estimated to achieve data enhancement, and on the other hand, effective integration is required to be performed on the multi-source heterogeneous data to achieve data complementation and correction. The method comprises the steps of utilizing basic data, physical test data, real sea test data, simulation analysis data and the like of the titanium alloy material in the deep and open sea environment to carry out registration and correlation on various monitoring and detection data of the titanium alloy material under the condition of single factor and multi-factor change, and providing a basis for subsequent data fusion and data modeling.
However, in the prior art, the prediction of the critical stress intensity factor of the stress corrosion can not be accurately predicted according to the existing corrosion data.
Disclosure of Invention
The embodiment of the invention provides a method for predicting the critical stress intensity factor of titanium alloy stress corrosion, which can accurately predict the critical stress intensity factor K of the stress corrosion by utilizing five parameters, namely the organization structure, the loading direction, the pressure, the temperature and the dissolved oxygen concentration of the titanium alloy to be predicted under the conditionISCC. The technical scheme is as follows:
the embodiment of the invention provides a method for predicting a critical stress intensity factor of titanium alloy stress corrosion, which comprises the following steps:
obtaining a training sample set and a test sampleA set, wherein each sample in the training sample set and the testing sample set comprises: tissue structure, direction of loading, pressure, temperature, dissolved oxygen concentration, and KISCC，KISCCRepresenting the critical stress intensity factor of stress corrosion;
inputting a training sample set into multiple different regression models for training, inputting a test sample set into the trained regression models for testing after training is finished, and obtaining K of each regression model according to a test resultISCCThe prediction accuracy of the predicted value; wherein the regression model comprises: a least square method fitting method, a gradient enhanced regression model and a random forest regression model;
inputting the tissue structure, loading direction, pressure, temperature and dissolved oxygen concentration of the titanium alloy to be predicted under the condition into a regression model with the highest prediction accuracy, and outputting KISCCAnd (5) predicting the value.
Further, the acquiring the training set and the test set includes:
performing experiments according to five parameters of the organization structure, the loading direction, the pressure, the temperature and the dissolved oxygen concentration of the titanium alloy under the condition to obtain corresponding stress corrosion critical stress intensity factors to form a sample set; wherein each sample in the set of samples comprises: organization structure, loading direction, pressure, temperature, dissolved oxygen concentration and stress corrosion critical stress intensity factor;
preprocessing a sample set, wherein the preprocessing comprises: processing missing values, feature codes and deleting outliers;
and dividing the preprocessed sample set into a training set and a testing set.
Further, the tissue structure comprises: equiaxed, bimodal, and weishi;
the loading direction includes: transverse and longitudinal directions.
Further, in the training, in the gradient enhanced regression model, the decision tree node number max _ depth is set to 3, and the learning algorithm number n _ estimators is set to 100.
Further, in training, in the random forest regression model, the tree n _ estimators of the tree is set to 100, the minimum number of samples required to split internal nodes min _ samples _ split is set to 2, the minimum number of samples required at leaf nodes min _ samples _ leaf is set to 1, and the minimum weighting score min _ weight _ fraction _ leaf in the sum of weights at all leaf nodes is set to 0.
Further, K of each regression model is obtained according to the test resultISCCThe prediction accuracy of the predicted values includes:
plotting K for each regression model outputISCCPredicted value and KISCCAnd comparing the real values with a curve graph, and obtaining the prediction accuracy of each trained regression model according to the comparison curve graph.
Further, inputting the tissue structure, the loading direction, the pressure, the temperature and the dissolved oxygen concentration of the titanium alloy to be predicted under the condition into a regression model with the highest prediction accuracy, and outputting KISCCThe predicted values include:
inputting the tissue structure, loading direction, pressure, temperature and dissolved oxygen concentration of the titanium alloy to be predicted under the condition into one regression model for prediction, and outputting KISCCPredicting a value;
according to the output KISCCK to which the predicted value belongsISCCSelecting the regression model with the highest prediction accuracy corresponding to the range for prediction to obtain the final KISCCAnd (5) predicting the value.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
in the embodiment of the invention, a training sample set and a test sample set are obtained; inputting a training sample set into multiple different regression models for training, inputting a test sample set into the trained regression models for testing after training is finished, and obtaining K of each regression model according to a test resultISCCThe prediction accuracy of the predicted value; wherein the regression model comprises: a least square method fitting method, a gradient enhanced regression model and a random forest regression model; inputting the tissue structure, loading direction, pressure, temperature and dissolved oxygen concentration of the titanium alloy to be predicted under the condition to be predicted to the highest prediction accuracyIn the regression model of (2), output KISCCAnd (5) predicting the value. Thus, the five parameters of the structure, the loading direction, the pressure, the temperature and the dissolved oxygen concentration of the titanium alloy to be predicted under the condition can be used for accurately predicting the critical stress intensity factor K of the stress corrosionISCC。
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for predicting a critical stress intensity factor of stress corrosion of a titanium alloy according to an embodiment of the present invention;
FIG. 2 shows the results of the least square fitting method (LS), the gradient enhanced regression model (GBR) and the random forest regression model (RFR) predicted by the three regression models, and KISCCA graph of the comparison curve of the real values;
fig. 3 is a schematic interface diagram of a system corresponding to the method for predicting the critical stress intensity factor of titanium alloy stress corrosion according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
As shown in fig. 1, an embodiment of the present invention provides a method for predicting a critical stress intensity factor of titanium alloy stress corrosion, including:
s101, a training sample set and a testing sample set are obtained, wherein each sample in the training sample set and the testing sample set comprises: tissue structure, direction of loading, pressure, temperature, dissolved oxygen concentration, and KISCC，KISCCRepresenting the critical stress intensity factor of stress corrosion;
in this embodiment, the acquiring the training set and the test set includes:
a1, performing experiments according to five parameters of the organization structure, the loading direction, the pressure, the temperature and the dissolved oxygen concentration of the titanium alloy under the condition of the titanium alloy to obtain corresponding stress corrosion critical stress intensity factors to form a sample set; wherein each sample in the set of samples comprises: organization structure (α%), loading direction, pressure (MPa), temperature (c), dissolved oxygen concentration (ppm), and stress corrosion critical stress intensity factor;
a2, preprocessing a sample set, wherein the preprocessing comprises: processing missing values, feature codes and deleting outliers;
in this embodiment, the texture structure is divided into equiaxial, bimodal, and weishi, and the codes are set as 0, 1, and 2, respectively; the loading direction is divided into horizontal direction and vertical direction, and the codes are respectively set as 1 and 2.
And A3, dividing the preprocessed sample set into a training set and a testing set.
In this embodiment, 80% of the preprocessed sample set may be randomly extracted as a training set, and the remaining 20% may be used as a testing set.
S102, generating a model: inputting a training sample set into multiple different regression models for training, inputting a test sample set into the trained regression models for testing after training is finished, and obtaining K of each regression model according to a test resultISCCThe prediction accuracy of the predicted value; wherein the regression model comprises: least squares fitting method (LS), gradient enhanced regression model (GBR), random forest regression model (RFR);
in this embodiment, during training, the number of decision tree nodes max _ depth is set to 3 and the number of learning algorithms n _ estimators is set to 100 in the gradient enhanced regression model.
In this embodiment, during training, in the random forest regression model, 100 is set for each tree n _ estimators, 2 is set for the minimum number of samples min _ samples _ split required for splitting internal nodes, 1 is set for the minimum number of samples min _ samples _ leaf required for leaf nodes, and 0 is set for the minimum weighting score min _ weight _ fraction _ leaf in the sum of weights at all leaf nodes.
In the present embodiment, the first and second electrodes are,obtaining K of each regression model according to test resultsISCCThe prediction accuracy of the predicted values includes:
plotting K for each regression model outputISCCPredicted value and KISCCThe comparison graph of the true values, according to which, as shown in fig. 2, there are 4 curves, respectively: kISCCK predicted by true value curve and least square method fitting method (LS)ISCCPredicted value curve, gradient enhanced regression model (GBR) predicted KISCCPredicted value curves and K predicted by random forest regression model (RFR)ISCCPredicted value curve with vertical axis representing KISCCThe horizontal axis represents the number of samples in the test set, and the comparison graph shows that: when K isISCC<At 85, the result predicted by a random forest regression model (RFR) is closest to the true value, namely the prediction accuracy is highest; when 85 is turned on<KISCC<At 90, the result predicted by a least square fitting method (LS) is closest to the true value; when 90 is reached<KISCC<At 120, the result predicted by a random forest regression model (RFR) is closest to the true value; when K isISCC>At 120, the results of the gradient enhanced regression model (GBR) predictions are closest to the true values.
S103, inputting the tissue structure, the loading direction, the pressure, the temperature and the dissolved oxygen concentration of the titanium alloy to be predicted under the condition into a regression model with the highest prediction accuracy, and outputting KISCCThe predicting value may specifically include the following steps:
b1, inputting the tissue structure, loading direction, pressure, temperature and dissolved oxygen concentration of the titanium alloy to be predicted under the condition into one regression model for prediction, and outputting KISCCPredicting a value;
b2, according to the output KISCCK to which the predicted value belongsISCCSelecting the regression model with the highest prediction accuracy corresponding to the range for prediction to obtain the final KISCCAnd (5) predicting the value.
In this embodiment, the values of the five parameters, i.e., the microstructure, the loading direction, the pressure, the temperature, and the dissolved oxygen concentration of the titanium alloy to be predicted, under the conditions thereof are first followed bySelecting a regression model for prediction and predicting KISCCK to which the predicted value belongsISCCThe range is selected, then the regression model with the highest prediction accuracy corresponding to the range is selected for prediction, and the final K under the parameter is obtainedISCCAnd (6) predicting the value. For example, K when the randomly selected regression model outputsISCCThe predicted value is 86, which indicates the associated KISCCThe range is as follows: 85<KISCC<90, selecting a least square method fitting method for prediction to obtain the final KISCCAnd (5) predicting the value.
The method for predicting the critical stress intensity factor of titanium alloy stress corrosion provided by this embodiment corresponds to the system interface, as shown in fig. 3.
In this embodiment, for a class of service materials of a titanium alloy, the result of the stress corrosion critical stress intensity factor is predicted by using five parameters, namely, the tissue structure, the loading direction, the pressure, the temperature, and the dissolved oxygen concentration of the titanium alloy to be predicted under the condition, so that the stress corrosion critical stress intensity factor prediction based on data driving is realized.
After the simulation experiment is carried out, the prediction method of the critical stress intensity factor of the titanium alloy stress corrosion can accurately predict the critical stress intensity factor K of the stress corrosion by inputting five parameters under the condition of the titanium alloy in the scene (such as deep sea and open sea) which is inconvenient for measuring the true value of the critical stress intensity factor of the titanium alloyISCCThe method is convenient and rapid, and provides a foundation for researching the corrosion rule of the deep and open sea material.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (7)

1. A method for predicting a critical stress intensity factor of titanium alloy stress corrosion is characterized by comprising the following steps:
acquiring a training sample set and a test sample set, wherein each sample in the training sample set and the test sample set comprises: group ofWeave structure, direction of loading, pressure, temperature, dissolved oxygen concentration, and KISCC，KISCCRepresenting the critical stress intensity factor of stress corrosion;
inputting a training sample set into multiple different regression models for training, inputting a test sample set into the trained regression models for testing after training is finished, and obtaining K of each regression model according to a test resultISCCThe prediction accuracy of the predicted value; wherein the regression model comprises: a least square method fitting method, a gradient enhanced regression model and a random forest regression model;
inputting the tissue structure, loading direction, pressure, temperature and dissolved oxygen concentration of the titanium alloy to be predicted under the condition into a regression model with the highest prediction accuracy, and outputting KISCCAnd (5) predicting the value.
2. The method of predicting the critical stress intensity factor for stress corrosion of titanium alloy according to claim 1, wherein said obtaining a training set and a test set comprises:
performing experiments according to five parameters of the organization structure, the loading direction, the pressure, the temperature and the dissolved oxygen concentration of the titanium alloy under the condition to obtain corresponding stress corrosion critical stress intensity factors to form a sample set; wherein each sample in the set of samples comprises: organization structure, loading direction, pressure, temperature, dissolved oxygen concentration and stress corrosion critical stress intensity factor;
preprocessing a sample set, wherein the preprocessing comprises: processing missing values, feature codes and deleting outliers;
and dividing the preprocessed sample set into a training set and a testing set.
3. The method for predicting the critical stress intensity factor of titanium alloy stress corrosion according to claim 1 or 2, wherein the texture structure comprises: equiaxed, bimodal, and weishi;
the loading direction includes: transverse and longitudinal directions.
4. The method for predicting the critical stress intensity factor of titanium alloy stress corrosion according to claim 1, wherein during training, a decision tree node number max _ depth is set to 3 and a learning algorithm number n _ estimators is set to 100 in the gradient enhanced regression model.
5. The method for predicting the stress corrosion critical stress intensity factor of titanium alloy according to claim 1, wherein during training, in the random forest regression model, setting the number of trees n _ estimators of the trees to be 100, the minimum number of samples required for splitting internal nodes to be min _ samples _ split to be 2, the minimum number of samples required at leaf nodes to be min _ samples _ leaf to be 1, and the minimum weighting fraction min _ weight _ action _ leaf in the total sum of weights at all leaf nodes to be 0.
6. The method for predicting the critical stress intensity factor of titanium alloy stress corrosion according to claim 1, wherein K of each regression model is obtained according to the test resultISCCThe prediction accuracy of the predicted value includes:
plotting K for each regression model outputISCCPredicted value and KISCCAnd comparing the real values with a curve graph, and obtaining the prediction accuracy of each trained regression model according to the comparison curve graph.
7. The method for predicting the critical stress intensity factor of titanium alloy stress corrosion according to claim 1, wherein the texture, the loading direction, the pressure, the temperature and the dissolved oxygen concentration of the titanium alloy to be predicted under the condition are input into a regression model with the highest prediction accuracy, and K is outputISCCThe predicted values include:
inputting the tissue structure, loading direction, pressure, temperature and dissolved oxygen concentration of the titanium alloy to be predicted under the condition into one regression model for prediction, and outputting KISCCPredicting a value;
according to the output KISCCK to which the predicted value belongsISCCSelecting the regression model with the highest prediction accuracy corresponding to the rangePredicting to obtain the final KISCCAnd (5) predicting the value.
CN202210158920.0A 2022-02-21 2022-02-21 Titanium alloy stress corrosion critical stress intensity factor prediction method Pending CN114580274A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210158920.0A CN114580274A (en) 2022-02-21 2022-02-21 Titanium alloy stress corrosion critical stress intensity factor prediction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210158920.0A CN114580274A (en) 2022-02-21 2022-02-21 Titanium alloy stress corrosion critical stress intensity factor prediction method

Publications (1)

Publication Number Publication Date
CN114580274A true CN114580274A (en) 2022-06-03

Family

ID=81773285

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210158920.0A Pending CN114580274A (en) 2022-02-21 2022-02-21 Titanium alloy stress corrosion critical stress intensity factor prediction method

Country Status (1)

Country Link
CN (1) CN114580274A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116110526A (en) * 2023-04-13 2023-05-12 深圳市正泰隆科技有限公司 Prediction method for critical stress intensity factor of titanium alloy stress corrosion

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116110526A (en) * 2023-04-13 2023-05-12 深圳市正泰隆科技有限公司 Prediction method for critical stress intensity factor of titanium alloy stress corrosion

Similar Documents

Publication Publication Date Title
Forth et al. On generating fatigue crack growth thresholds
Lozovan et al. Forming the toolset for development of a system to control quality of operation of underground pipelines by oil and gas enterprises with the use of neural networks
Nair et al. Acoustic emission pattern recognition in CFRP retrofitted RC beams for failure mode identification
Zhang et al. Probabilistic estimation of flexural loading capacity of existing RC structures based on observational corrosion-induced crack width distribution using machine learning
Allahyari et al. A new approach to determine strength of Perfobond rib shear connector in steel-concrete composite structures by employing neural network
Wang et al. Machine learning-based fatigue life prediction of metal materials: Perspectives of physics-informed and data-driven hybrid methods
CN114580274A (en) Titanium alloy stress corrosion critical stress intensity factor prediction method
Mishra Artificial intelligence algorithms for the analysis of mechanical property of friction stir welded joints by using python programming
Guo et al. Bayesian prediction of the stress concentration effect on high-strength wires with corrosion pits
Sharma et al. A polygonal FEM and continuum damage mechanics based framework for stochastic simulation of fatigue life scatter in duplex microstructure titanium alloys
Derakhshani On the uncertainty analysis of uplift capacity of suction caissons in clay based on the fuzzy sets theory
Heng et al. Machine Learning-Assisted probabilistic fatigue evaluation of Rib-to-Deck joints in orthotropic steel decks
Sun et al. Prediction of chloride ion concentration distribution in basalt-polypropylene fiber reinforced concrete based on optimized machine learning algorithm
Ai et al. Crack detection and evolution law for rock mass under SHPB impact tests
Gao et al. A novel defect-based fatigue damage model coupled with an optimized neural network for high-cycle fatigue analysis of casting alloys with surface defect
Li et al. Notch fatigue life prediction of micro-shot peened 25CrMo4 alloy steel: A comparison between fracture mechanics and machine learning methods
Fletcher et al. Image analysis to reveal crack development using a computer simulation of wear and rolling contact fatigue
Zhong et al. Fatigue crack growth of EH36 steel in air and corrosive marine environments
CN115618751B (en) Steel plate mechanical property prediction method
CN111797456A (en) Prediction method for mechanical property degradation rule of steel bar after rusting
Yatian et al. Residual life prediction method for remanufacturing sucker rods based on magnetic memory testing and a support vector machine model
Qi et al. A CNN-based method for concreate crack detection in underwater environments
CN115879218A (en) Method for predicting life of observation window of deep sea manned submersible based on finite element analysis
Aursand et al. Remaining fatigue life assessment of corroded mooring chains using crack growth modelling
CN112032578B (en) Method and equipment for measuring parameters of corrosion point in pipeline

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