[MAP Logo]

Materials Algorithms Project
Program Library


Program MAP_NEURAL_EPSILON_MS

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

Provenance of Source Code

Hong-Seok Yang
Computational Metallurgy Laboratory,
Graduate Institute of Ferrous Metallurgy (GIFT),
Pohang University of Science and Technology (POSTECH),
Pohang, Republic of Korea Added to MAP: January 2011

Top | Next

Purpose

Prediction of the epsilon martensite-start temperature (MS) as a function of chemical composition

Top | Next | Prev

Specification

Language: C
Product form: Source code / Executable files
Operating System: Linux / Window

Top | Next | Prev

Description

MAP_NEURAL_EPSILON_MS contains programs which enable the user to predict the epsilon martensite-start temperature as a function of chemical composition. The neural network model was made based on literature data using Models Manager, Neuromat Ltd.

MINMAX
A text file containing the minimum and maximum limits of each input and output variable
test.dat
An input text file containing the input variables used for predictions. Each colum represents C, Mn, Ni, Cr, Al, Si, Mo, Co, Cu, Nb, Ti, V and W in wt %, respectively.
model.gen
This is a unix command file. It can be excuted by typing csh model.gen at the command prompt.
MODEL.exe
This is executable program for the PC correspond to the unix command file.
Result
An output text file. Each colum represents (MS), (Uncertainty), (MS-Uncertainty) and (MS+Uncertainty) in K respectively.

Top | Next | Prev

References

H.-S. Yang, J. H. Jang, H. K. D. H. Bhadeshia and D. W. Suh. Critical Assessment: Martensite-Start Temperature for the &\gamma; to ε Transformation, will be published

Top | Next | Prev

Parameters

Input parameters

Input parameters are chemical compositions in wt %. test.dat file contains the parameters.

Output parameters

Output parameters are predicted epsilon Ms in K. Result file contains the parameters.

Top | Next | Prev

Error Indicators

None.

Top | Next | Prev

Accuracy

None.

Top | Next | Prev

Further Comments

None.

Top | Next | Prev

Example

1. Program text

 Complete program.

2. Program data

Input data are in test.dat, an example is as follow:

0 20 0 0 0 4 0 0 0 0 0 0 0

0 20 0 0 0 5 0 0 0 0 0 0 0

0 20 0 0 0 6 0 0 0 0 0 0 0

0 20 0 0 0 7 0 0 0 0 0 0 0

3. Program results

Result data are in Result or Model_RESULT.dat, an example is as follow:

428.731140 17.975042 410.756073 446.706177

424.012604 18.601940 405.410645 442.614532

410.479828 19.760050 390.719757 430.239868

386.650360 24.472645 362.177704 411.123016

Top | Next | Prev

Auxiliary Routines

None

Top | Next | Prev

Keywords

neural network, epsilon martensite start-temperature

Top | Next | Prev

Download

Linux:
Download Neural_Epsilon_Ms model (tar.gz file, 3.8 Mbytes)
PC Software:
Download Neural_Epsilon_Ms model (zip file, 2.9Mbytes)
Top | Prev