[MAP Logo]

Materials Algorithms Project
Program Library



Program MAP_STEEL_FATIGUE_LIFE_PREDICTOR

  1. Provenance of code.
  2. Purpose of code.
  3. Specification.
  4. Description of program's operation.
  5. References.
  6. Parameter descriptions.
  7. Error indicators.
  8. Accuracy estimate.
  9. Any additional information.
  10. Example of code
  11. Auxiliary routines required.
  12. Keywords.
  13. Download source code.
  14. Links.

Provenance of Source Code

C. N. Hulme-Smith
Phase Transformations Group,
Department of Materials Science and Metallurgy,
University of Cambridge,
27 Charles Babbage Road,
Cambridge, CB3 0FS, U.K.

E-mail: C. N. Hulme-Smith

Added to MAP: July 2018.

Top | Next

Purpose

This program - the Fatigue Life Predictor for Steels (FLiPS) - uses an artificial neural network to predice the fatigue life for steels, based on their mechanical properties and test conditions. FLiPS uses a large database obtained from the Japanese National Research Institute for Metals (NRIM) fatigue data sheets, which are available fre-of-charge online. The data were used as an input to an artificial neural network, via Neuromat Model Manager software by Thomas Sourmail. The artificial neural network itself is built using the code Bigback5 by David MacKay.

FLiPS was originally written for the InnovateUK project Series production of Lightweight parts by Isostatic pressing of Metal powders to give Material and Energy Reduction (SLIMMER).

Top | Next | Prev

Specification

Language:Qt5
Product form:Graphical User Interface and QT project file
Platform:Mac - tested on MacOS 10.13 (High Sierra) and MacOS 10.14 (Mojave); Windows - tested on Windows 10 only. The executables and accompanying files do not call external libraries and so they may well be compatible with earlier versions, but this has not been tested and is not guaranteed.

Complete program.

Top | Next | Prev

Description

FLiPS is a graphical interface for artificial neural networks that can simulate the fatigue life of steels in uniaxial, torsion or four-point bending loading. The input date were taken from fatigue data sheets published on the Japanese National Research Institute for Metals website. Neuromat Model Manager was used as a graphical interface to train the network, which was built using David MacKay's Bigback5 program.

The coefficients and matrices for the neural network were extracted after training and are hard-coded into FLiPS, which allows the user to calculate the expected fatigue life by simply entering simple mechanical properties and testing conditions into the graphical window. Uncertainties may also be calculated, if desired, which are calculated from coefficients that are derived using Bayesian statistics during the training of the model. These coefficients account for both uncertainty due to a lack of input data at the given value of each input parameter and the sensitivity of the network to variations about each specified input.

Dimitriu & Bhadeshia showed that fatigue crack growth rates can be predicted using an artificial neural network from mechanical properties and test conditions. FLiPS uses a similar approach to estimate fatigue life. Since artificial neural networksa are very flexible, they can capture complex physical relationships between input parameters and output, even if the analytical dependence is not known. In some cases, this leads to overfitting of data. However, Bigback5 penalises large dependencies, so they are only accepted if they lead to significant improvements in the predictions. A subset of the input data is also removed from the network training and is then used to test the fit. Both of these safeguard reduce the likelihood of overfitting the input data and lead to more robust neural networks. More information is provided in the documentation of Neuromat Model manager and in the technical note in reference 4.

For each of Mac and Windows, an executable is provided, along with supporting files. To run the model, simply double-click the executable, fill in the information required and press "Predict". These files must be kept in the same directory as the executable for the program to function correctly. A PDF user guide is also provided and may be copied to wherever the user wishes, but a copy must be kept in the same directory as the executable to ensure correct functionality of the "Help" button.

Files:

FLiPS.exe (Windows), FLiPS.app (Mac) Executable.
FLiPS_source_data.dat Input data used to train the artificial neural network, in tab-delimited text format.
User manual User manual for the graphical interface.
FLiPS.pro Qt project file for FLiPS. This may be opened in Qt creator to develop the program.
FLiPS.pro.user Ancillary Qt project file for FLiPS. This must be in the same directory as FLiPS.pro
main.cpp C++ file that contains the instructions for calling the main program (mainwindow.cpp).
mainwindow.cpp C++ file tcontianing all commands to perform calculations. The files …_lu_parameters.txt are hard-coded inside this file, which is why it is over 20 MB in size.
mainwindow.h File containing commands to create all buttons in the graphical user interface.
mainwindow.ui File containing the geometry and design of the window for the graphical user interface.
bending_lu_paramters.txt Matrix of the lower-upper (LU) decomposition for the weights associated with the four-point bending fatigue neural network.
torsion_lu_paramters.txt Matrix of the lower-upper (LU) decomposition for the weights associated with the torsional fatigue neural network.
uniaxial_lu_paramters.txt Matrix of the lower-upper (LU) decomposition for the weights associated with the uniaxial fatigue neural network.
FLiPS_logo.icns Icon file to give the graphical interface a dedicated icon in the Mac dock and the title bar of the graphical window. No icon files have been created for use in Windows.

Follow the steps listed below to use the program:

Top | Next | Prev

References

  1. R. C. Dimitriu & H. K. D. H. Bhadeisha, Fatigue Crack Growth Rate Model for Metallic Alloys, Materials and Design, 31 (2010) 2134-2139.
  2. D. J. C. MacKay, Bigback5, Online, available from http://www.inference.org.uk/mackay/bigback/bigback5.tar.gz, accessed on 17 June 2017.
  3. T. Sourmail, Neuromat Model Manager, Online, available from http://www.thomas-sourmail.net/neural_networks_model_manager.html, accessed on 17 June 2017.
  4. M. J Peet, Technical Note: Bayesian Neural Networks as Implemented in Model Manager, 2015, Online, available from http://www.mathewpeet.org/notes/BNNMM/ModelManager+BayesianNeuralNetworks.pdf, accessed on 17 June 2017.
  5. Japanese National Research Institute for Metals Fatigue Data Sheets, Online, available from https://smds.nims.go.jp/openTest/en/content/fatiguelist.html, accessed on 14 March 2017.

Top | Next | Prev

Parameters

Input parameters

Temperature Unit - radio button list
Unit of measurement for the test temperature. Can be Celsius, Farenheit or Kelvin.

Toughness type - radio button list
Type of toughness data available. Can be Charpy toughness in J -2 or fracture toughness in MPa m½.

Stress type / MPa - radio button list
Decide how the test stress is defined: as a strss range, a stress amplitud, a mean stress, a maximum (most tensilt/least compressive)stress or a minimum (most compressive/least tensile) stress. All stresses must be given in MPa.

Yield strength — Real
Yield strength of the material in MPa.

Toughness — Real
Toughness of the material in the units specified by the user in the Toughness type radio button.

Elongation — Real
Elongation to failure of the material, expressed in percentage strain.

Reduction of area — Real
Reduction of area at failure of the material, given in percentage of original area.

Ultimate tensile strength — Real
Ultimate tensile strength of the material, given in MPa.

Temperature — Real
Temperature used for predictions, i the units specified by the user in the Temperature Unit radio button.

Cycle frequency — Real
Frequency of the test used for prediction of the fatigue life. Given in Hz (cycles per second).

Stress concentration factor — Real
Allows the user to specif a stress concentration factor if the fatigue life of a notched or flawed specimen is to be predicted. Can be set to 1.0 if a standard, smooth and defect-free sampel is to be used for predictions.

Stress — Real
The stress of the test that will be used for the prediction. The stress should be that specified by the user using the Stress type / MPa radio button list.

Effective R factor — Real
R factor used for predictions. This is defined as the ratio of minimum to maximum stress, with positive stresses beign taken as tensield and negative stresses defined as compressive. For example, a maximum stress of 500 MPa (tensile) and a minimum stress of 20 MPa (tensile) would give R = 25. Similarly, a maximum stress of 100 MPa tensile) and 200 MPa (compressive) would be R = -0.5.

Calculate uncertainties — checkbox
Ticking this box results in uncertainties in the predictions being displayed.

Output parameters

Nf — Real
Predicted number of cycles to failure.

Uncertainty (below Nf) — Real
Uncertainty factor in the prediction. Since the range of fatigue lives covers many orders of magnitude, the artificial neural network is base don the decadic logarithms of fatigue lives. This is converted to a number of cycles for the final display. Since the logarithms of fatigue lives are given ± an uncertainty, the actual number of cycles is given ×/÷ the uncertainty, according to the algebraic laws of logarithms.

Top | Next | Prev

Error Indicators

Should a number result in a negative logarithm during the calculation, "NAN" will be displayed in the appropriate field after a prediction. Errors encountered by the user during the building of any future Qt project are specified in the Qt documentation.

Top | Next | Prev

Accuracy

An uncertainty estimation is provided, which is a factor by which the fatigue life may vary, within the confidence of the model, as explained in the Output section.

Top | Next | Prev

Further Comments

None.

Top | Next | Prev

Example

Screenshot of FLiPS prediction and input data.

Top | Next | Prev

Auxiliary Routines

None.

Top | Next | Prev

Keywords

fatigue life, artificial neural network, Bayesian statistics, graphical user interface.

Top | Next | Prev

Download

Windows executable and associated files.

Mac executable and associated files.

Files needed to build a new graphical user interface using Qt creator. This will allow future development of the program or the deployment to new operating systems (e.g. Linux, Android, iOS).

Standalone user manual.

Top | Prev


MAP originated from a joint project of the National Physical Laboratory and the University of Cambridge.

Top | Program Index | MAP Homepage | Valid XHTML 1.0 Transitional