[MAP Logo]

Materials Algorithms Project
Program Library


  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

Murugananth M
Phase Transformations Group,
Department of Materials Science and Metallurgy,
University of Cambridge,
Cambridge CB2 3QZ, U.K.

The neural network program was produced by:

David MacKay,
Cavendish Laboratory,
University of Cambridge,
Madingley Road,
Cambridge, CB3 0HE, U.K.

E-mail: Murugananth

Added to MAP: May 2002.

Top | Next


To predict the Creep Rupture Strength of plates and welds.

Top | Next | Prev


Language:  C,FORTRAN, Shell script
Product form:  Source code / executables
Platform :  Solaris, Linux

Complete program.

Top | Next | Prev


A program for the estimation of the creep life of ferritic steels as a function of elemental composition, test conditions and solution treatment.

Description of the files and their usage in the present module :
Readme Tells the name of the input variables and the order in which these are to be presented in a file named anndata_example before using the model for predictions.
anndata_example A file having the base composition of the alloy that is to be analysed. "example" is the identification of the alloy here. And the file name from which test.dat is generated. One can resonably modify this file to step as many variables as there are. The format of this file is
[base composition] [minimum] [maximum] [step] [1(=step) or 0 (=use value from base comp)] [variable name]
RESULT_example Directory where the predicted results of an alloy with identification name "example" can be found.
run This file has to be used to predict. Either execute it with the command "csh run" or "./run". This would take you through all the processes and at the end will let you know the place where your results can be located.
Directory "bin"
MINMAX Contains the minimum and maximum ranges of each input variable.
test.dat Contains the input variables which will be used by accessory programs to make predictions.
data_no.c A C-file to get the number of data in test.dat file via keyboard input.
predict A file containing the shell commands.
generate44 This is the executable file for the neural network program. It reads the normalised input data file, norm_test.in, and uses the weight files in subdirectory c, to find a value for ferrite number.The results are written to the temporary output file _out. 
spec.c  Specification file to be read by generate44.
_ot, _out, _res, _sen These files are created by generate44 and can be deleted. 
Directory sbin
Agen_data_tmp To step the variables which are denoted in the file "anndata_example"
Aget_result To split the results if many variables are varied simultaneously
log To log or anitlog the results from predictions.
Directory where weight files for use by the generate44 pertaining to each model in the committee are stored.
d Directory where the normalised values of inputs and output are stored
outprdt Directory where the output from generate44 are written to.
committee.dat Consists of values representing the number of models in committee and number of variables used.
normtest.for  Program to normalise the input data read from test.dat. Also produces the normalised input file norm_test.in. It makes use of information read in from no_of_rows.dat and committee.dat.
gencom.for  This program uses the information in committee.dat and combines the predictions from the individual models, in subdirectory outprdt, to obtain an averaged value (committee prediction). The output (in normalised form) is written to com.dat. 
treatout.for  Program to un-normalise the committee results in com.dat and write the output predictions to unnorm_com. This file is then renamed as result.

Instructions to run the module

Top | Next | Prev


  1. D. G. Cole, C. Martin-Moran, A. G. Sheard, H. K. D. H. Bhadeshia and D. J. C. MacKay, 1999, Science and Technology of Welding and Joining, Accepted for publication.
  2. D.J.C. MacKay, 1997, Mathematical Modelling of Weld Phenomena 3, eds. H Cerjak & H.K.D.H. Bhadeshia, Inst. of Materials, pp 359.
  3. D.J.C MacKay's website at http://wol.inference.phy.cam.ac.uk/mackay/README.html#Source_code
Top | Next | Prev


Input parameters

Output parameters

Directory having the result files with format predictions,predictions-error, predictions+error

Top | Next | Prev

Error Indicators


Top | Next | Prev


No information supplied.

Top | Next | Prev

Further Comments


Top | Next | Prev


1. Program text

Complete program.

2. Program data

See file anndata_example

3. Program results

Refer example file in example directory  : RESULT_example
Top | Next | Prev

Auxiliary Routines


Top | Next | Prev


Creep Rupture Strength, Power plant steels, Chromium steels

Top | Next | Prev

Download source code

(Download the files according to the platform Unix or Linux and then gunzip <filename> followed by tar -xvf <filename>)

Top | Prev

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


TopProgram Index | MAP HomepageValid HTML 3.2!