CN116306301A - Storage tank thermal buckling failure prediction method based on neural network - Google Patents
Storage tank thermal buckling failure prediction method based on neural network Download PDFInfo
- Publication number
- CN116306301A CN116306301A CN202310300770.7A CN202310300770A CN116306301A CN 116306301 A CN116306301 A CN 116306301A CN 202310300770 A CN202310300770 A CN 202310300770A CN 116306301 A CN116306301 A CN 116306301A
- Authority
- CN
- China
- Prior art keywords
- storage tank
- characteristic parameters
- flame
- neural network
- data
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 24
- 238000004088 simulation Methods 0.000 claims abstract description 25
- 238000003062 neural network model Methods 0.000 claims abstract description 9
- 238000011156 evaluation Methods 0.000 claims abstract description 4
- 238000013016 damping Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 6
- 230000005855 radiation Effects 0.000 description 5
- 229910000831 Steel Inorganic materials 0.000 description 4
- 239000010959 steel Substances 0.000 description 4
- 238000004880 explosion Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000002195 synergetic effect Effects 0.000 description 3
- 230000006378 damage Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000035939 shock Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 206010000369 Accident Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- 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
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- 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
- G06F2119/08—Thermal analysis or thermal optimisation
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E30/00—Energy generation of nuclear origin
- Y02E30/30—Nuclear fission reactors
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a storage tank thermal buckling failure prediction method based on a neural network. The method can realize rapid prediction and evaluation of the thermal buckling failure of the storage tank, lays a foundation for the safety detection of the storage tank, and ensures the storage safety of oil gas: the method mainly comprises five steps: step one, collecting characteristic parameters of a storage tank; performing hot buckling simulation on the storage tank by adopting finite element software, so as to obtain the lowest critical temperature under different storage tank characteristic parameters; step three, collecting characteristic parameters of the storage tank in actual working conditions; step four, a neural network model after the thermal buckling behavior of the storage tank is invalid is established, characteristic parameters of the storage tank adopted in simulation are used as input, the lowest critical temperature obtained in simulation is used as output, and the neural network is trained; fifthly, safely predicting the failure of the storage tank according to the lowest critical temperature; the flow of the steps of the method is shown in the abstract drawing.
Description
Technical Field
The invention belongs to the field of tank field safety research, and particularly relates to a storage tank thermal buckling failure prediction method based on a neural network.
Background
Storage tanks are the primary storage means for oil and gas, and are used in large scale in numerous oil depot storage bases as important storage facilities. With the continuous development of petrochemical industry in China, the large-scale of the storage tank and the continuous expansion of the scale of a tank field are meant, and the safety of the storage tank becomes particularly important.
With the increasing consumption of oil and gas, large steel storage tanks are widely used as important facilities for industrial and strategic energy storage. Depending on the geometry, the tanks are generally divided into: vertical cylindrical storage tank, horizontal cylindrical storage tank and spherical storage tank. The steel vertical cylindrical storage tank has the characteristics of small occupied area and low cost, and is widely applied to various chemical industry parks. The integrated design of the construction and the facilities of the oil storage tank area becomes the direction of the construction and the development of the China oil depot, if a serious fire accident occurs to a large oil gas storage tank, domino effect can be possibly caused, and the storage tank is easy to be subjected to the synergistic effect of fire heat radiation and explosion shock waves.
Due to the different orders of magnitude of the duration of the fire load and the explosion load, there is only a spatial synergistic effect and no temporal synergistic effect. The reason is that the duration of the explosive load is only several milliseconds to several hundred milliseconds, while the duration of the fire load is much longer, and the fire heat radiation has a delayed injury effect, so that the determination of the vulnerability and the ineffectiveness of the storage tank under the fire heat radiation has important significance for the safety of oil gas.
Currently, the thermal buckling research method of the storage tank under the fire heat radiation is mainly numerical simulation and CFD simulation. The numerical simulation is to perform numerical solution by adopting a finite element method, and perform linear buckling analysis by adopting a boundary element method and an isogeometric analysis method, so as to evaluate buckling modes and critical temperature values and simultaneously predict buckling temperature by using geometric nonlinear analysis. CFD simulation is to model a fire near a target storage tank by using one of the most commonly used CFD software at present, namely a Fire Dynamics Simulator (FDS), and then to perform thermal structure analysis by using finite element software ANSYS Workbench. By adopting a transient heat transfer implicit method, a Finite Element Model (FEM) for thermal structure analysis realized in an ANSYS Workbench is built, and the joint loading of neighbor pool fire and explosion shock waves to a thin-wall steel storage tank is realized. Or an ABAQUS finite element transient heat transfer model is adopted to determine the temperature change of the side wall of the target tank as a function of the fire passing time, so that the thermal buckling behavior of the storage tank is predicted. However, these two prediction methods require a lot of calculation time, and the division of the grids also affects the prediction result for the finite element method, so that the damaged structure cannot be accurately predicted and positioned when the hot buckling behavior of the storage tank occurs.
Based on the analysis, in the field of tank farm safety research, a simple, rapid and accurate method for predicting the thermal buckling failure of the storage tank is urgently needed to ensure the storage safety of oil gas.
Therefore, the invention provides a storage tank thermal buckling failure prediction method based on a neural network. The thermal buckling of the storage tank occurs under the action of fire, and the thermal deformation of the storage tank is aggravated along with the rise of the fire temperature, so that the damage failure of the storage tank is caused. According to the method, the temperature field distribution of the target storage tank is calculated by utilizing finite element analysis software, the thermal post-buckling behavior of the storage tank is solved by using an artificial damping method, and based on the principle, the thermal buckling failure of the storage tank can be rapidly predicted by combining an artificial neural network learning method. The method does not need to actually measure the heat radiation data of the storage tank, is simple to operate and rapid to analyze, and has important significance for safety evaluation of the storage tank.
Disclosure of Invention
The invention provides a storage tank thermal buckling failure prediction method based on a neural network. The method can realize rapid prediction and evaluation of the thermal buckling failure of the storage tank, lays a foundation for safety detection of the storage tank, and ensures the storage safety of oil gas. The method is characterized in that firstly, the initial temperature of the environment is determined to be 20 ℃, finite element analysis software is adopted to perform thermal buckling simulation on a steel storage tank, the diameter, the height and the wall thickness of the storage tank, the net distance between the storage tank and flame, the flame height and the flame diameter are continuously changed in the simulation process, and the storage tank data under different working conditions are collected; secondly, collecting sample data of different storage tanks according to characteristic parameters of the storage tanks in the database; and thirdly, taking sample data of the storage tank as input, taking a thermal buckling result simulated by finite element software as output, training a neural network model, and accurately predicting thermal buckling failure of the storage tank based on the neural network model obtained by training.
The storage tank thermal buckling failure prediction method based on the neural network mainly comprises the following steps:
(1) The characteristic parameters of the storage tank are collected, the characteristic parameters of the storage tank have important influence on the finite element thermal buckling simulation, and the characteristic parameters must be confirmed before the simulation, including the material of the storage tank, the diameter, the height and the wall thickness of the storage tank, the net distance between the storage tank and the flame, the flame height and the flame diameter.
(2) And simulating the finite element thermal buckling of the storage tank, and obtaining the thermal buckling behavior of the storage tank under different characteristic parameters by changing the characteristic parameters of the storage tank. And carrying out fitting by using finite element software to obtain temperature fitting curves under different characteristic parameters.
(3) And collecting characteristic parameters of the storage tank in the actual working condition, and comparing the characteristic parameters of the storage tank adopted by the finite element software simulation to analyze the characteristic parameters of the storage tank to obtain characteristic parameters of the actual storage tank and obtain a database.
(4) And establishing a neural network model after the thermal buckling behavior of the storage tank fails, taking the characteristic parameters of the storage tank adopted during simulation as input, taking the lowest critical temperature obtained during simulation as output, and training the neural network according to the result obtained through finite element software simulation. The input of the neural network consists of the material of the storage tank, the diameter, the height, the wall thickness of the storage tank, the net distance between the storage tank and the flame, the flame height and the flame diameter.
(5) And (5) failure prediction. Based on the established neural network model, the characteristic parameters of the storage tank under the actual working condition, namely the data of the characteristic parameters of the storage tank to be predicted, are taken as input, so that the minimum critical temperature of the storage tank when hot buckling occurs can be obtained, the storage tank failure can be safely predicted according to the minimum critical temperature, and protection and guarantee measures are taken in advance.
Drawings
Flow chart of implementation of thermal buckling failure prediction method of storage tank of fig. 1 fig. 2 neural network structure diagram fig. 3 storage tank lowest critical simulation value and prediction value comparison diagram
Characteristic parameters of the tank of FIG. 4
Detailed Description
The following detailed description of the invention will be presented in conjunction with the drawings to provide those skilled in the art with an understanding and appreciation of the advantages, features and steps of the invention and to make a more accurate definition of the scope of the invention.
The storage tank hot buckling failure prediction method based on the neural network mainly comprises five steps, wherein the flow is shown in the accompanying drawings, and the specific steps are as follows:
step one: characteristic parameters of the storage tank are collected, including the material of the storage tank, the diameter of the storage tank, the height, the wall thickness, the net distance between the storage tank and the flame, the flame height and the flame diameter. The characteristic parameters of the tank may be obtained from the design data, construction data and completion data of the tank.
Step two: performing hot buckling simulation on the storage tank by adopting finite element software, so as to obtain the lowest critical temperature under different storage tank characteristic parameters; the finite element software adopts an ADM algorithm (Artificial Damping Method ) which has effectiveness on the phenomena of thermal buckling and local buckling, and the ADM algorithm also increases the artificial damping force when considering the total external load and internal force of the structure, so as to establish the balance of the three. When the model is stable, the damping ratio is small enough, and the artificial damping energy does not influence the overall balance of the model; when local buckling occurs in certain areas of the structure, the node displacement of the area changes, so that damping energy also changes along with the change of the corresponding node speed, therefore, when the value of the damping ratio changes rapidly, buckling occurs in the local area, namely when the artificial damping ratio changes suddenly, the thermal buckling behavior of the storage tank occurs, and the corresponding temperature is the lowest critical temperature. In the process of simulating data, the distance between the storage tank and the flame is required to be 4m, the flame diameter is required to be 2m, and the flame position height is required to be 4m, so that characteristic data (X, Y, Z) of a group of storage tanks are obtained, then the corresponding minimum critical temperature (W) is simulated through finite element software, and the artificial damping ratio is required to be adopted as a critical measurement standard for the occurrence of thermal buckling of the storage tanks during finite element simulation.
Step three: collecting characteristic parameters of the storage tank in actual working conditions, and analyzing the characteristic parameters of the storage tank according to finite element software simulation, so as to obtain basic characteristic parameters of the storage tank to be predicted; sample parameters can be obtained by finite element software simulation, including the distance between the storage tank and the flame, the diameter of the flame, the position height of the flame and the minimum critical temperature. And the storage tank sample data with the same characteristic parameters are at least 10 groups, and in the hot buckling failure prediction of the storage tank, at least 10 groups of sample data with the same characteristic parameters as the storage tank to be predicted need to be extracted to form a data structure shown in table 1.
TABLE 1 data structure
Step four: establishing a neural network model after the thermal buckling behavior of the storage tank is invalid, taking 13 groups of data as training samples according to the result obtained by simulation of finite element software, taking the characteristic parameters of the storage tank adopted during simulation as input, taking the lowest critical temperature obtained by simulation as output, and training the neural network; according to the data structure of table 1, the input layer of the neural network comprises 3 nodes corresponding to the distance between the storage tank and the flame, the diameter of the flame and the position height of the flame, and the output layer comprises 1 node corresponding to the lowest critical temperature of the thermal buckling behavior of the storage tank; the middle layer of the neural network is set as 1 layer, and the number of nodes is set as 10; the structure of the neural network is shown in figure 2; 13 sets of data are simultaneously used as 13 test data; the training function was set to the Lai Wen Beige-Marquardt method (Levenberg-Marquard algorithm).
Step five: and (5) failure prediction. Based on the neural network model established in the step 5, the characteristic parameters of the storage tank under the actual working condition, namely the data of the characteristic parameters of the storage tank to be predicted, are taken as input, so that the lowest critical temperature of the storage tank when thermal buckling occurs can be obtained, and the failure of the storage tank can be safely predicted according to the lowest critical temperature.
The method of the invention is used for predicting the failure property of the storage tank after the hot buckling by combining the storage tank:
first, according to the method in the first step, characteristic parameters of the storage tank are collected. The material of the storage tank is Q345, and in the windless state; the diameter of the target tank is 20m; the center distance between the target tank and the flame is 40m; the detailed parameters are shown in figure 4.
And step two, changing the distance between the storage tank and the flame, the diameter of the flame and the position height of the flame according to the method in the step two, and adopting finite element software to perform thermal buckling simulation on the storage tank so as to obtain the lowest critical temperature under different storage tank characteristic parameters.
And thirdly, collecting characteristic parameters of the storage tank in actual working conditions according to the method in the third step, and obtaining basic characteristic parameters of the storage tank to be predicted.
And fourthly, training the neural network according to the method in the fourth step, and storing the trained network. The tank minimum critical temperature fit curve is shown in figure 3.
And fifthly, selecting the distance between any storage tank and flame, the diameter of the flame and the position height of the flame by adopting a neural network obtained through training, and predicting the minimum buckling temperature of the storage tank to perform failure prediction.
Claims (1)
1. A storage tank thermal buckling failure prediction method based on a neural network is characterized in that finite element software is adopted to realize rapid prediction and evaluation of storage tank thermal buckling failure, and the method mainly comprises the following steps:
step one: collecting characteristic parameters of the storage tank, including the material of the storage tank, the diameter, the height and the wall thickness of the storage tank, the net distance between the storage tank and the flame, the flame height and the flame diameter; the characteristic parameters of the storage tank can be obtained by inquiring design data, construction data and completion data of the storage tank;
step two: performing hot buckling simulation on the storage tank by adopting finite element software, so as to obtain the lowest critical temperature under different storage tank characteristic parameters; the finite element software adopts an ADM algorithm (Artificial Damping Method ), the method has effectiveness on the phenomena of thermal buckling and local buckling, and the ADM algorithm also increases artificial damping force when considering the total external load and internal force of the structure, so as to establish the balance of the three; when the model is stable, the damping ratio is small enough, and the artificial damping energy does not influence the overall balance of the model; when local buckling occurs in certain areas of the structure, the node displacement of the area changes, so that damping energy also changes along with the change of the corresponding node speed, therefore, when the value of the damping ratio changes rapidly, buckling occurs in the local area, namely when the artificial damping ratio changes suddenly, the thermal buckling behavior of the storage tank occurs, and the corresponding temperature is the lowest critical temperature; in the process of simulating data, the distance between the storage tank and the flame is required to be 4m, the flame diameter is required to be 2m, and the flame position height is required to be 4m, so that characteristic data (X, Y, Z) of a group of storage tanks are obtained, then the corresponding minimum critical temperature (W) is simulated through finite element software, and the artificial damping ratio is required to be adopted as a critical measurement standard for the occurrence of thermal buckling of the storage tanks during finite element simulation;
step three: collecting characteristic parameters of the storage tank in actual working conditions, and analyzing the characteristic parameters of the storage tank according to finite element software simulation, so as to obtain basic characteristic parameters of the storage tank to be predicted; the sample parameters can be obtained through finite element software simulation, and comprise the distance between a storage tank and flame, the diameter of the flame, the position height of the flame and the minimum critical temperature, and the storage tank sample data with the same characteristic parameters are at least 10 groups, and in the thermal buckling failure prediction of the storage tank, at least 10 groups of sample data with the same characteristic parameters as the storage tank to be predicted need to be extracted to form a data structure shown in the table 1;
TABLE 1 data structure
Step four: establishing a neural network model after the thermal buckling behavior of the storage tank is invalid, taking 13 groups of data as training samples according to the result obtained by simulation of finite element software, taking the characteristic parameters of the storage tank adopted during simulation as input, taking the lowest critical temperature obtained by simulation as output, and training the neural network; according to the data structure of table 1, the input layer of the neural network comprises 3 nodes corresponding to the distance between the storage tank and the flame, the diameter of the flame and the position height of the flame, and the output layer comprises 1 node corresponding to the lowest critical temperature of the thermal buckling behavior of the storage tank; the middle layer of the neural network is set as 1 layer, and the number of nodes is set as 10; the structure of the neural network is shown in figure 2; 13 sets of data are simultaneously used as 13 test data; the training function is set to the Lai Wen Beige-Marquardt method (Levenberg-Marquard algorithm);
step five: and (5) failure prediction. Based on the neural network model established in the step 5, the characteristic parameters of the storage tank under the actual working condition, namely the data of the characteristic parameters of the storage tank to be predicted, are taken as input, so that the lowest critical temperature of the storage tank when thermal buckling occurs can be obtained, and the failure of the storage tank can be safely predicted according to the lowest critical temperature.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310300770.7A CN116306301A (en) | 2023-03-26 | 2023-03-26 | Storage tank thermal buckling failure prediction method based on neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310300770.7A CN116306301A (en) | 2023-03-26 | 2023-03-26 | Storage tank thermal buckling failure prediction method based on neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116306301A true CN116306301A (en) | 2023-06-23 |
Family
ID=86813006
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310300770.7A Pending CN116306301A (en) | 2023-03-26 | 2023-03-26 | Storage tank thermal buckling failure prediction method based on neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116306301A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117113788A (en) * | 2023-10-25 | 2023-11-24 | 南京南工应急科技有限公司 | Method for predicting structural failure of steel normal-pressure storage tank under coupling of fire and explosion |
-
2023
- 2023-03-26 CN CN202310300770.7A patent/CN116306301A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117113788A (en) * | 2023-10-25 | 2023-11-24 | 南京南工应急科技有限公司 | Method for predicting structural failure of steel normal-pressure storage tank under coupling of fire and explosion |
CN117113788B (en) * | 2023-10-25 | 2023-12-29 | 南京南工应急科技有限公司 | Method for predicting structural failure of steel normal-pressure storage tank under coupling of fire and explosion |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103455682B (en) | A method of prediction hp-ht well corrosion set pipe residue lifetime | |
CN114186456B (en) | Time interval fracture state based near field dynamics method for structural impact elastoplastic fracture analysis | |
CN113361192A (en) | Boiler internal heating surface wall temperature safety monitoring and evaluating system | |
CN116306301A (en) | Storage tank thermal buckling failure prediction method based on neural network | |
EP3229156B1 (en) | Predicting cracking in cooled metal or alloy components | |
CN110210681A (en) | A kind of prediction technique of the monitoring station PM2.5 value based on distance | |
CN115994465A (en) | Method for evaluating damage effect kNN of unexpected explosion air shock wave to bridge | |
CN109871642B (en) | Temperature field modeling method for internal structure of steam generator | |
CN114048670B (en) | Intelligent algorithm for rapidly evaluating damage of regional concrete bridge after earthquake | |
CN115422630A (en) | Method for evaluating dynamic response and damage degree of concrete gravity dam structure under action of explosive load | |
CN117113788B (en) | Method for predicting structural failure of steel normal-pressure storage tank under coupling of fire and explosion | |
CN117421560A (en) | Reinforced concrete member impact resistance protection design and disaster assessment method | |
Ke et al. | Sensitivity analysis and estimation method of natural frequency for large cooling tower based on field measurement | |
CN111209692A (en) | Structural temperature field numerical calculation method based on equivalent convective heat transfer coefficient | |
CN112434369B (en) | Structural load sensing method based on machine learning | |
CN103514329B (en) | Substation's lightning rod tower safety assessment method | |
Toktaş et al. | Artificial neural networks solution to display residual hoop stress field encircling a split-sleeve cold expanded aircraft fastener hole | |
Bai et al. | A reliability analysis and optimization method for a turbine shaft under combined high and low cycle fatigue loading | |
CN115544794A (en) | Fatigue life prediction-based support steel frame design parameter selection method | |
Saab | Non-linear finite element analysis of steel frames in fire conditions. | |
CN103337000A (en) | Safety monitoring and prewarning method for oil-gas gathering and transferring system | |
Remennikov et al. | Prediction of airblast loads in complex environments using artificial neural networks | |
Zhang | [Retracted] Application of Particle Swarm Algorithm in Nanoscale Damage Detection and Identification of Steel Structure | |
CN105844002A (en) | LS-DYNA based method for optimally designing layout of storage tank area of chemical industry park | |
Pepin et al. | A probabilistic analysis of a nonlinear structure using random fields to quantify geometric shape uncertainties |
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 |