CN107092733A - The lithium ion battery mechanical strength Forecasting Methodology searched for based on Automatic Neural Networks - Google Patents
The lithium ion battery mechanical strength Forecasting Methodology searched for based on Automatic Neural Networks Download PDFInfo
- Publication number
- CN107092733A CN107092733A CN201710220180.8A CN201710220180A CN107092733A CN 107092733 A CN107092733 A CN 107092733A CN 201710220180 A CN201710220180 A CN 201710220180A CN 107092733 A CN107092733 A CN 107092733A
- Authority
- CN
- China
- Prior art keywords
- lithium ion
- ion battery
- mechanical strength
- neural networks
- input
- 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
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
- G06F30/23—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
- G06F2119/06—Power analysis or power optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Tests Of Electric Status Of Batteries (AREA)
Abstract
The present invention relates to a kind of lithium ion battery mechanical strength Forecasting Methodology searched for based on Automatic Neural Networks, including：Step S1：Determine input, the output parameter of neutral net；Step S2：Finite element modeling is carried out, data sample is collected and is used as training sample；Step S3：Formulate lithium ion battery mechanical strength model；Step S4：Collected data sample is input to the lithium ion battery mechanical strength model formulated in step S3, data sample is trained；Step S5：Predict lithium ion battery mechanical strength；Step S6：Simulating, verifying, the accuracy and robustness of judgment models are carried out to model.The present invention is the lithium ion battery mechanical strength Forecasting Methodology built using Automatic Neural Networks searching method, electric automobile is predicted being subjected to impact lower lithium ion battery mechanical strength suddenly using the model, reliable basis are provided for road safety, the model that the present invention is built under uncertain and dynamic input condition is accurate and robust.
Description
Technical field
The present invention relates to the assessment of electric automobile energy storage system mechanical strength, it is based on certainly in particular to one kind
The lithium ion battery mechanical strength Forecasting Methodology of dynamic neutral net search.
Background technology
The energy storage systems such as the lithium ion battery of electric automobile are modeled based on physical model and empirical model, with
The state of electric automobile energy storage system is assessed, is the focus of current research.By the summary to fuel cell modelling method, find
Based on artificial intelligence（AI）The modeling of method can with it is integrated in systems.But when input changes, its robustness and
Accuracy is still a very big challenge to brainstrust.For example, the change of internal battery pack temperature and discharge rate and due to
Suddenly change caused by road grade or friction condition may cause battery status monitoring to produce larger error, so as to cause
Poorly efficient monitoring to electric vehicle battery group.Meanwhile, when battery pack is when suddenly by external impact or collision, few people are closed
Note the assessment to battery machine intensity.Therefore, for the consideration of road safety, the assessment of battery machine intensity is for battery production
It is significantly, because this influence unpredictalbe caused by collision may be led for business and automaker
The blast in pond is sent a telegraph, or even occurs fire.
The content of the invention
It is an object of the invention to provide a kind of lithium ion battery mechanical strength prediction searched for based on Automatic Neural Networks
Method, the Automatic Neural Networks based on FInite Element（ANS）Searching method, develops and is based on when battery is by unexpected impact
Displacement, the lithium ion battery mechanical strength model of three kinds of inputs of temperature and strain rate.
In order to realize above-mentioned purpose, adopt the following technical scheme that.It is a kind of based on Automatic Neural Networks search for lithium from
Sub- battery machine intensity prediction method, it is characterised in that including：
Step S1：According to electric automobile in the case where being subjected to impact suddenly, the change of lithium ion battery major parameter and its driving is pacified
Full influence, determines input, the output parameter of neutral net；
Step S2：Finite element modeling is carried out to lithium ion battery, data sample is collected and is used as training sample；
Step S3：Set based on data sample and given Automatic Neural Networks and formulate lithium ion battery mechanical strength model, and
Two kinds of uncertainty is taken into account；
Step S4：Collected data sample is divided into two parts in certain proportion, and is input in step S3 and is formulated
Lithium ion battery mechanical strength model, data sample is trained；
Step S5：Only selection coefficient correlation is more than the Automatic Neural Networks model of a certain determination value as further analysis lithium ion
The model of battery machine intensity, predicts lithium ion battery mechanical strength；
Step S6：Simulating, verifying, the accuracy and robustness of judgment models are carried out to model.
The Automatic Neural Networks automatically select the activation letter in neuronal quantity, hidden layer and output layer in hidden layer
Number and training algorithm, the hidden layer include the neuron of unknown number, and the Automatic Neural Networks are searched through using various
Training algorithm sets the neuronal quantity in hidden layer, and the activation primitive in hidden layer and output layer is by the weightings of data
Summation is converted to one and is clearly worth.
The mechanism of the Automatic Neural Networks search is to be based on artificial neural network（ANN）, by input layer, hidden layer and defeated
Go out layer composition, the input layer with input quantity identical neuron by constituting, i.e. displacement, temperature, strain rate, the output layer
It is made up of single output mechanical strength.
Step S2 includes：On finite element analysis software, the material property of lithium ion battery is first defined, then application boundary
Condition simulation lithium ion battery obtains data sample of the lithium ion battery in the case where being impacted suddenly to the mechanical response of imposed load
This.
The uncertainty of described two types is the distribution of the change and input set.
Based on artificial intelligence（AI）Modeling method there is in terms of its parameter setting uncertainty, its parameter setting changes
Change can significantly affect the ability of model prediction battery status.The change of the setting is that the Automatic Neural Networks search will
The setting of change, including network type, the activation primitive of hidden layer and output layer, training algorithm, the quantity of hidden neuron.
The network type includes multilayer perceptron and RBF, the activation primitive bag of the hidden layer and output layer
Include Identity, Gauss, sine, hyperbola, index and logical function.
The external or internal factor such as impact or vibration may cause the nonsystematic of displacement, temperature and the strain rate of battery
Property change, this will significantly affect the prediction of battery strength.Normal distribution is pressed in the input of the lithium ion battery mechanical strength model
Change.The distribution of the input assumes that selected N number of input（Such as displacement, temperature, strain rate）Change by normal distribution,
And tolerance and standard deviation are determined based on experiment and error approach, it is used to evaluate battery machine strength model robustness to produce
Distribution sample.
Step S6 includes：Under the condition of uncertainty of N number of input, using numerical simulation software, to based on automatic nerve net
Model of the network by optimization is emulated, and the Automatic Neural Networks model is loaded in computer programming language, such as C, C++
Deng.
In the emulation, it is assumed that each input followed normal distribution distribution, wherein minimum value and maximum are arranged to identical
Input, and by the way that other inputs are remained into their average value, each input of analysis acts solely on lithium ion battery
When, the influence to its mechanical strength.
Compared with prior art, the present invention is strong using the lithium ion battery machinery of Automatic Neural Networks searching method structure
Forecasting Methodology is spent, electric automobile is predicted being subjected to impact lower lithium ion battery mechanical strength suddenly using the model, is
Road safety provides reliable basis, and the model that the present invention is built under uncertain and dynamic input condition is accurate and robust
's.
Brief description of the drawings
Fig. 1 is method flow schematic diagram of the invention；
The boundary condition schematic diagram that Fig. 2 applies for the present invention on cylindrical 18650 lithium ion battery；
Power and the comparison diagram of experimental data that Fig. 3 passes through model prediction for the present invention.
Embodiment
With reference to embodiment and accompanying drawing, the invention will be further described.
Embodiment, a kind of lithium ion battery mechanical strength Forecasting Methodology searched for based on Automatic Neural Networks, flow such as Fig. 1
It is shown.
Step S1：Battery is caused to produce mechanical force and stress by external impact or displacement.Mechanical force is mechanical strength
Factor, therefore output is selected as in the present invention.The temperature of battery ambient and the strain produced also influence the machinery of battery strong
Degree.Therefore, in the present invention including three inputs, respectively displacement, temperature and strain rate.
Step S2：Under mechanical load and the combined influence of temperature, the mechanical model of lithium ion battery passes through finite element skill
Art is modeled.
A. ABAQUS/Explicit softwares of 6.14 versions, first definition material characteristic are used.The part of lithium ion battery
Including various parts, such as battery case, rubber roll, composite, isolator.In the present embodiment, modeling battery is 18650 lithiums
Ion battery, the battery case that rubber roll is surrounded in modeling is steel, and the rubber roll that modeling forms battery is crushable foam, therefore selection
The consistent mechanical model of rubber roll.It can accurately replicate 18650 lithium ion batteries load and displacement and can be with from experiment
It was observed that short-circuit generation, and greatly reduce the calculating time.
B. it is that application boundary condition carrys out mechanical response of the simulated battery to imposed load with that.Fig. 2 is given in battery
The boundary condition applied in group.One end of battery is fixed, and the other end of battery is given inward displacement to realize compression.
Repeat to simulate by changing the environment temperature in the predefined field settings of ABAQUS.
C. the validity of simulation model is examined, is obtained by experiment, the compression stress and Germicidal efficacy predicted by simulation model
Gained is very consistent.Hence, it can be determined that FEM model may be used as obtaining the compression stress of displacement, strain rate and temperature change
The effective tool of data.In fig. 2, when no application load, battery pack keeps its stable structure.The application of pressure causes
Battery case and rubber roll structure it is broken.It should also be noted that stress accumulation in rubber roll is than observing on battery case
Stress is much higher.
Step S3：Automatic Neural Networks based on table 1 set to formulate lithium ion battery mechanical strength model.In the present invention
In, it is proposed that the artificial intelligence approach for the formulation of lithium ion battery mechanical strength model.Automatic Neural Networks searching method
Mechanism be based on artificial neural network（ANN）, it is made up of input layer, hidden layer and output layer.Input layer is by with inputting quantity
Identical neuron is constituted.It is following three, displacement, temperature, strain rate in the present embodiment.Output layer is by single defeated
Going out --- mechanical strength is constituted.Hidden layer is made up of the neuron of unknown number, is set by using various training algorithms hidden
Hide the neuronal quantity in layer.Automatic Neural Networks are automatically selected in neuronal quantity, hidden layer and output layer in hidden layer
Activation primitive and training algorithm, activation primitive in hidden layer and output layer by the weighted sum of data be converted to one it is clear
Value.
In order to ensure the accuracy and robustness of the model when battery is subjected to temperature, strain rate and the dynamic change of displacement,
The uncertainty of following two types is added to method.
(1) change set：
The setting to be changed of Automatic Neural Networks searching method includes network type（Multilayer perceptron（MLP）And RBF
（RBF））, activation primitive（Identity, Gauss, sine, hyperbola, index and logical function）Hide and output neuron, instruction
Practice the selection of algorithm and the quantity of hidden neuron,
The Automatic Neural Networks parameter setting table of table 1
It is arranged in table 1 and shows used in the present embodiment.
(2) distribution of input：
The present embodiment selects three inputs（Displacement, temperature and strain rate), change by normal distribution.Their tolerance and standard deviation
Difference is selected based on experiment and error approach, to produce the distribution sample for the robustness for being used to evaluate battery machine strength model.
Step S4：Data are divided into 7：The lithium ion battery mechanical strength mould formulated in 10 ratio input step S3
Data are trained by type.
Step S5：Only Automatic Neural Networks model of the selection coefficient correlation more than 0.95 is used as analysis lithium ion battery machinery
The model of intensity；Test result indicates that, with activation function（Such as Logistic and Tanh（Hidden layer）And Identity（It is defeated
Enter layer）With training algorithm BFGS）Automatic Neural Networks model perform more preferably than other combinations set, as shown in Figure 3.It
There is higher coefficient correlation on the training data, and there is in training and test data minimum error difference.
Step S6：Simulating, verifying is carried out to model.Using the battery model after optimization in three inputs（Displacement, should
Variability and temperature）Condition of uncertainty under carry out model emulation.This is primarily to whether inspection model provides suitable value
（Non-negative）And mechanical strength can be predicted exactly.Emulation is devised on STATISTICA, wherein model is in C or C ++ journey
Loaded in sequence.In the design of Simulation, it is assumed that each input followed normal distribution distribution, wherein minimum value and maximum is arranged to phase
Same input.As a result show：For 8000 simulation runs, Automatic Neural Networks model can provide rational mechanical strength
Value, it is shown that the robustness of the nonsystematic variable in input.
In addition, by inputting the method for remaining their average value by other, having obtained machine of each variable to battery
The influence degree of tool intensity.As a result clearly illustrate, the mechanical strength of battery（Power）Increase with the increase of strain rate and displacement
Greatly, reduce with the rise of temperature.The analysis is very consistent with experimental result, due to the increase of external impact, causes it
Bigger displacement is produced, therefore produces higher mechanical stress with strain to resist impact.And the rise of temperature causes battery
It is due to that the hardness and toughness of battery is reduced at relatively high temperatures that mechanical strength is relatively low.Temperature and the combined effect of displacement are in machinery
Show than other input combinations in terms of intensity generation higher non-linear.From the analysis it may be concluded that displacement and temperature
The minimum value of higher mechanical strength should be kept for battery, so that it is guaranteed that battery possesses longer life-span, more preferable reliability
And security.
Claims (10)
1. a kind of lithium ion battery mechanical strength Forecasting Methodology searched for based on Automatic Neural Networks, it is characterised in that including：
Step S1：According to electric automobile in the case where being subjected to impact suddenly, the change of lithium ion battery major parameter and its driving is pacified
Full influence, determines input, the output parameter of neutral net；
Step S2：Finite element modeling is carried out to lithium ion battery, data sample is collected and is used as training sample；
Step S3：Set based on data sample and given Automatic Neural Networks and formulate lithium ion battery mechanical strength model, and
Two kinds of uncertainty is taken into account；
Step S4：Collected data sample is divided into two parts in certain proportion, and is input in step S3 and is formulated
Lithium ion battery mechanical strength model, data sample is trained；
Step S5：Only selection coefficient correlation is more than the Automatic Neural Networks model of a certain determination value as further analysis lithium ion
The model of battery machine intensity, predicts lithium ion battery mechanical strength；
Step S6：Simulating, verifying, the accuracy and robustness of judgment models are carried out to model.
2. the lithium ion battery mechanical strength Forecasting Methodology according to claim 1 searched for based on Automatic Neural Networks, its
It is characterised by, the Automatic Neural Networks automatically select the activation in neuronal quantity, hidden layer and output layer in hidden layer
Function and training algorithm, the hidden layer include the neuron of unknown number, and the Automatic Neural Networks are searched through using each
Plant training algorithm to set the neuronal quantity in hidden layer, the activation primitive in hidden layer and output layer adds data
Power summation is converted to one and is clearly worth.
3. the lithium ion battery mechanical strength Forecasting Methodology according to claim 1 searched for based on Automatic Neural Networks, its
It is characterised by, the mechanism of the Automatic Neural Networks search is to be based on artificial neural network, by input layer, hidden layer and output layer
Composition, the input layer with input quantity identical neuron by being constituted, and the output layer is made up of mechanical strength.
4. the lithium ion battery mechanical strength Forecasting Methodology according to claim 1 searched for based on Automatic Neural Networks, its
It is characterised by, step S2 includes：On finite element analysis software, the material property of lithium ion battery is first defined, then using side
Boundary's condition simulation lithium ion battery obtains data of the lithium ion battery in the case where being impacted suddenly to the mechanical response of imposed load
Sample.
5. the lithium ion battery mechanical strength Forecasting Methodology according to claim 1 searched for based on Automatic Neural Networks, its
It is characterised by, the uncertainty of described two types is the distribution of the change and input set.
6. the lithium ion battery mechanical strength Forecasting Methodology according to claim 5 searched for based on Automatic Neural Networks, its
It is characterised by, the change of the setting is that the Automatic Neural Networks search for the setting to be changed, including network type, hidden layer
With the quantity of the activation primitive, training algorithm, hidden neuron of output layer.
7. the lithium ion battery mechanical strength Forecasting Methodology according to claim 6 searched for based on Automatic Neural Networks, its
It is characterised by, the network type includes multilayer perceptron and RBF, the activation primitive of the hidden layer and output layer
Including Identity, Gauss, sine, hyperbola, index and logical function.
8. the lithium ion battery mechanical strength Forecasting Methodology according to claim 5 searched for based on Automatic Neural Networks, its
It is characterised by, the distribution of the input assumes that selected N number of input is changed by normal distribution, and tolerance and standard deviation base
Determined in experiment and error approach, to produce the distribution sample for being used for evaluating battery machine strength model robustness.
9. the lithium ion battery mechanical strength Forecasting Methodology according to claim 1 searched for based on Automatic Neural Networks, its
It is characterised by, step S6 includes：Under the condition of uncertainty of N number of input, using numerical simulation software, to based on automatic nerve net
Model of the network by optimization is emulated, and the Automatic Neural Networks model is loaded in computer programming language.
10. the lithium ion battery mechanical strength Forecasting Methodology according to claim 9 searched for based on Automatic Neural Networks, its
It is characterised by, in the emulation, it is assumed that each input followed normal distribution distribution, wherein minimum value and maximum are arranged to identical
Input, and by the way that other inputs are remained into their average value, each input of analysis acts solely on lithium ion battery
When, the influence to its mechanical strength.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710220180.8A CN107092733A (en) | 2017-04-06 | 2017-04-06 | The lithium ion battery mechanical strength Forecasting Methodology searched for based on Automatic Neural Networks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710220180.8A CN107092733A (en) | 2017-04-06 | 2017-04-06 | The lithium ion battery mechanical strength Forecasting Methodology searched for based on Automatic Neural Networks |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107092733A true CN107092733A (en) | 2017-08-25 |
Family
ID=59649039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710220180.8A Pending CN107092733A (en) | 2017-04-06 | 2017-04-06 | The lithium ion battery mechanical strength Forecasting Methodology searched for based on Automatic Neural Networks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107092733A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108717475A (en) * | 2018-02-07 | 2018-10-30 | 浙江大学城市学院 | A kind of lithium battery monomer machinery intensive probable model based on hybrid simulation method |
| CN109299552A (en) * | 2018-09-29 | 2019-02-01 | 清华大学 | A kind of appraisal procedure and its assessment system of battery power status |
| CN109376933A (en) * | 2018-10-30 | 2019-02-22 | 成都云材智慧数据科技有限公司 | Lithium ion battery negative material energy density prediction technique neural network based |
| CN110274815A (en) * | 2019-05-06 | 2019-09-24 | 中国汽车技术研究中心有限公司 | A kind of analysis method of inside lithium ion cell construction machine intensity |
| CN112462779A (en) * | 2020-11-30 | 2021-03-09 | 汕头大学 | Group robot dynamic capture control method and system based on gene regulation network |
| CN114564872A (en) * | 2022-03-15 | 2022-05-31 | 重庆大学 | Extrusion stress prediction method for battery pack system |
| CN116186942A (en) * | 2023-04-23 | 2023-05-30 | 中国航发四川燃气涡轮研究院 | Aeroengine compressor disk temperature prediction method based on multilayer perceptron |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101504443A (en) * | 2008-02-05 | 2009-08-12 | 比亚迪股份有限公司 | Prediction method for discharge capacity of lithium ion battery |
| CN103186101A (en) * | 2011-12-27 | 2013-07-03 | 中联重科股份有限公司 | Hardware-in-loop simulation test system of vehicle control unit |
| CN105095962A (en) * | 2015-07-27 | 2015-11-25 | 中国汽车工程研究院股份有限公司 | Method for predicting dynamic mechanical property of material based on BP artificial neural network |
| CN205544414U (en) * | 2016-02-04 | 2016-08-31 | 汕头大学 | Open adaptable batteries of electric vehicle energy storage system |
-
2017
- 2017-04-06 CN CN201710220180.8A patent/CN107092733A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101504443A (en) * | 2008-02-05 | 2009-08-12 | 比亚迪股份有限公司 | Prediction method for discharge capacity of lithium ion battery |
| CN103186101A (en) * | 2011-12-27 | 2013-07-03 | 中联重科股份有限公司 | Hardware-in-loop simulation test system of vehicle control unit |
| CN105095962A (en) * | 2015-07-27 | 2015-11-25 | 中国汽车工程研究院股份有限公司 | Method for predicting dynamic mechanical property of material based on BP artificial neural network |
| CN205544414U (en) * | 2016-02-04 | 2016-08-31 | 汕头大学 | Open adaptable batteries of electric vehicle energy storage system |
Non-Patent Citations (2)
| Title |
|---|
| AKHIL GARG ETC.: ""Design of robust battery capacity model for electric vehicle by incorporation of uncertainties"", 《WILEY ONLINE LIBRARY》 * |
| ELHAM SAHRAEI ETC.: ""Calibration and finite element simulation of pouch lithium-ion batteries for mechanical integrity", 《JOURNAL OF POWER SOURCES》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108717475A (en) * | 2018-02-07 | 2018-10-30 | 浙江大学城市学院 | A kind of lithium battery monomer machinery intensive probable model based on hybrid simulation method |
| CN108717475B (en) * | 2018-02-07 | 2022-02-11 | 浙江大学城市学院 | Lithium battery monomer mechanical strength probability model modeling method based on hybrid simulation method |
| CN109299552A (en) * | 2018-09-29 | 2019-02-01 | 清华大学 | A kind of appraisal procedure and its assessment system of battery power status |
| CN109376933A (en) * | 2018-10-30 | 2019-02-22 | 成都云材智慧数据科技有限公司 | Lithium ion battery negative material energy density prediction technique neural network based |
| CN110274815A (en) * | 2019-05-06 | 2019-09-24 | 中国汽车技术研究中心有限公司 | A kind of analysis method of inside lithium ion cell construction machine intensity |
| CN112462779A (en) * | 2020-11-30 | 2021-03-09 | 汕头大学 | Group robot dynamic capture control method and system based on gene regulation network |
| CN112462779B (en) * | 2020-11-30 | 2023-07-25 | 汕头大学 | Dynamic group robot trapping control method and system based on gene regulation network |
| CN114564872A (en) * | 2022-03-15 | 2022-05-31 | 重庆大学 | Extrusion stress prediction method for battery pack system |
| CN116186942A (en) * | 2023-04-23 | 2023-05-30 | 中国航发四川燃气涡轮研究院 | Aeroengine compressor disk temperature prediction method based on multilayer perceptron |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107092733A (en) | The lithium ion battery mechanical strength Forecasting Methodology searched for based on Automatic Neural Networks | |
| Hong et al. | Vehicle energy system active defense: a health assessment of lithium‐ion batteries | |
| CN114117840A (en) | Structural performance prediction method based on simulation and test data hybrid drive | |
| Dou et al. | Health diagnosis of concrete dams using hybrid FWA with RBF-based surrogate model | |
| Benabou | Development of LSTM networks for predicting viscoplasticity with effects of deformation, strain rate, and temperature history | |
| Gornet et al. | A new isotropic hyperelastic strain energy function in terms of invariants and its derivation into a pseudo-elastic model for Mullins effect | |
| Mustafa et al. | Probabilistic micromechanical analysis of composite material stiffness properties for a wind turbine blade | |
| Li et al. | Mechanical safety prediction of a battery-pack system under low speed frontal impact via machine learning | |
| Strauss et al. | Inverse statistical nonlinear FEM analysis of concrete structures | |
| Bouras et al. | Prediction of high-temperature creep in concrete using supervised machine learning algorithms | |
| Xu et al. | Data-driven modelling and evaluation of a battery-pack system’s mechanical safety against bottom cone impact | |
| Xie et al. | A life prediction method of mechanical structures based on the phase field method and neural network | |
| Srinivas et al. | Computational methodologies for vibration-based damage assessment of structures | |
| Wang et al. | Continual residual reservoir computing for remaining useful life prediction | |
| CN115422630A (en) | Method for evaluating dynamic response and damage degree of concrete gravity dam structure under action of explosive load | |
| CN108805419B (en) | Power grid node importance calculation method based on network embedding and support vector regression | |
| Farhat et al. | Towards a dynamic data driven system for structural and material health monitoring | |
| KAMYAB et al. | Reliability assessment of structures by Monte Carlo simulation and neural networks | |
| Bisht et al. | A data-driven intelligent hybrid method for health prognosis of lithium-ion batteries | |
| Zhang et al. | Enhancing battery pack safety against cone impact using machine learning techniques and Gaussian noise | |
| Millwater et al. | Probabilistic damage tolerance analysis for general aviation | |
| Hussain et al. | Development of an artificial neural network (ANN) constitutive model for mechanical metamaterials | |
| CN115169111B (en) | Random forest based energetic material mechanical property prediction method and storage device | |
| Dan et al. | Intelligent platform for model updating in a structural health monitoring system | |
| Machavaram et al. | Identification of crack in a structural member using improved radial basis function (IRBF) neural networks |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170825 |
|
| WD01 | Invention patent application deemed withdrawn after publication |