MAP Logo

Materials Algorithms Project
Steels: Program Library

[A logo showing the University of Cambridge Crest]


  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. Capdevila, F.G. Caballero, and C. García de Andrés

Department of Physical Metallurgy


Centro Nacional de Investigaciones Metalúrgicas (CENIM- CSIC)

Avda. Gregorio del Amo, 8

E- 28040 Madrid



Added to MAP: September 2005.

Top | Next


Isothermal austenite-to-pearlite transformation has been analyzed using a neural network technique within a Bayesian framework. In this framework, the growth rate of pearlite can be represented as a general empirical function of variables such as Mn, Cr, Ni, Si and Mo alloying contents and temperature which are of great important for the pearlite growth mechanisms.

.Top | Next | Prev


Language: FORTRAN / C
Product form: Source code / Executable files
Operating Selntem: Windows 98, 2K, XP

Top | Next | Prev


MAP_STEEL_PEARLITE_GROWTH  contains a program which enable the user to estimate the growth rate of pearlite for any temperature as a function of chemical composition. It makes use of a neural network program called generate44, which was developed by David MacKay and is part of the bigback5 program. The network was trained using a large database of experimental results [1].  The source code for the neural network program can be downloaded from David MacKay's website; the executable files only are available from MAP.

Programs are available which run Windows 95/98,2K and XP. A set of program and data files are provided for the model, which calculate the intrlamellar spacing for pearlite. The files for Windows are included in a directory called GROWTH.ZIP. This directory contains the following files and subdirectories:


A brief file with instructions for running the program.


A list of the input variables.


A text file containing the minimum and maximum limits of each input and output variable. This file is used to normalise and unnormalise the input and output data.


An input text file containing the input variables used for predictions, together with an example set of data.


This is the executable file for the neural network program. It reads the normalised input data file, (created by normalise) , and uses the weight files in subdirectory c, to find a value for the output. The results are written to the temporary output file _out.


Contains the normalised input data.


Contains the final un-normalised committee results for the predicted output.



The weights files for the different models.


Files containing information for calculating the size of the error bars for the different models.


Files containing information about the perceived significance value for each model.


Files containing values for the noise, test error and log predictive error for each model.



A normalised output file which was created during the building of the model. It is accessed by generate44 via spec.t1.



The normalised output file containing the committee results. It is generated by .gencom.

Top | Next | Prev


  1. D.J.C. MacKay, 1997, Mathematical Modelling of Weld Phenomena 3, eds. H. Cerjak and H.K.D.H. Bhadeshia, Inst. of Materials, London, pp 359.
  2. F. G. Caballero, C. Capdevila and C. García de Andrés, Neural Network Model for Isothermal Pearlite Transformation. Part II: Growth Rate Model, ISIJ Internacional, Vol. 45, 2005, 238-247. 

Top | Next | Prev


Input parameters

The input variables for each module are listed in the labels.txt file in the corresponding directory. The maximum and minimum values for each variable are given in the file MINMAX.

Manganese - Mn
Manganese content (wt.-%).

Silicon - Si
Silicon content (wt.-%).

Chromium - Cr
Chromium content (wt.-%).

Molybdenum - Mo
Molybdenum content (wt.-%).
Nickel - Ni
Nickel content (wt.-%).
Temperature - T
Isothermal temperature (ºC).

Output parameters

Gowth rate - Go
Decimal logarithm of pearlite growth rate (mm/s).

Top | Next | Prev

Error Indicators


Top | Next | Prev


A full calculation of the error bars is presented in reference 2.

Top | Next | Prev

Further Comments


Top | Next | Prev


1. Program text

Complete program.

2. Program data

Mn   Si   Cr   Mo   Ni   T
0.00 0.00 0.00 0.00 0.00 603.00
0.25 0.00 0.00 0.00 0.00 597.83
0.50 0.00 0.00 0.00 0.00 592.65
0.75 0.00 0.00 0.00 0.00 587.48
1.00 0.00 0.00 0.00 0.00 582.30
1.25 0.00 0.00 0.00 0.00 577.13
1.50 0.00 0.00 0.00 0.00 571.95
1.75 0.00 0.00 0.00 0.00 566.78

3. Program results

LogGo    Error    LogGo-error LogGo+error

1.776106 0.201040 1.575065 1.977146

1.565999 0.229596 1.336403 1.795595

1.358631 0.289172 1.069460 1.647803

1.155519 0.341250 0.814269 1.496769

0.957901 0.379094 0.578806 1.336995

0.766906 0.405570 0.361336 1.172476

0.582803 0.426941 0.155862 1.009743

0.405101 0.450040 -0.044939 0.855141

Top | Next | Prev

Auxiliary Routines


Top | Next | Prev


Pearlite, Isothermal growth rate, Steels

Top | Next | Prev


Download Windows Module

Top | Prev