Materials Algorithms Project
Program Library

Program MAP_STEEL_LOWTEMPER

Provenance of code.
Purpose of code.
Specification.
Description of subroutine's operation.
References.
Parameter descriptions.
Error indicators.
Accuracy estimate.
Any additional information.
Example of code
Auxiliary subroutines required.
Keywords.
Download source code.
Links.

Provenance of Source Code

D. Gaude-Fugarolas,
Phase Transformations Group,
Department of Materials Science and Metallurgy,
University of Cambridge,
Cambridge, U.K.

The neural network program was produced by:

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

Added to MAP: 2005

Top | Next

Purpose

Estimation of the evolution of hardness (Vickers) during tempering of Fe-0.55C-0.22Si-0.77Mn-0.2Cr-0.15Ni-0.05Mo-0.001V wt% steel at the range of temperatures in which only diffusion of carbon and precipitation of carbides occur, without any recovery or recrystallisation.

Top | Next | Prev

Specification

Language:	FORTRAN / C
Product form:	Source code / Executable files

Top | Next | Prev

Description

MAP_STEEL_LOWTEMPER contains a trained model to estimate the change in hardness in quenched carbon steel during tempering at low temperature. It is considered low temperature the range in which only diffusion of carbon and precipitation of carbides occur, excluding any substantial recovery or recrystallisation. The model is based on an Avrami reaction rate equation implemented by training an artificial neural network on a small but very accurate database of experimental results. The model obtained has one single submodel in committee. The training of the model makes use of a neural network program called generate44, which was developed by David MacKay and is part of the bigback5 program. The model is trained using an interface developed by Sourmail. The source code for the neural network program can be downloaded from David MacKay's website; the executable files only are available from MAP. The downloadable package contains the following files and subdirectories:

MINMAX: 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.
test.dat: An input text file containing the input variables used for predictions.
model.gen: This is a unix shell file containing the command steps required to run the module. It can be executed by typing csh model.gen at the command prompt. This shell file compiles and runs all the programs necessary for normalising the input data, executing the network for each model, unnormalising the output data and combining the results of each model to produce the final committee result.
spec.t1: A dynamic file, created by spec.ex, which contains information about the module and the number of data items being supplied. It is read by the program generate44.
norm_test.in: This is a text file which contains the normalised input variables. It is generated by the program normtest.for in subdirectory s.
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. The results are written to the temporary output file _out.
_ot, _out, _res, _sen: These files are created by generate44 and can be deleted.
Result: Contains the final un-normalised committee results for the predicted hardness.
SUBDIRECTORY s
spec.c: The source code for program spec.ex.
normtest.for: Program to normalise the data in test.dat and produce 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 Result.
committee.dat: A text file containing the number of models to be used to form the committee result and the number of input variables. It is read by gencom.for, normtest.for and treatout.for.
SUBDIRECTORY c
_w_*f: The weights files for the different models.
_*.lu: Files containing information for calculating the size of the error bars for the different models.
_c_*: Files containing information about the perceived significance value [1] for each model.
_R_*: Files containing values for the noise, test error and log predictive error [1] for each model.
SUBDIRECTORY d
outran.x: A normalised output file which was created when developing the model. It is accessed by generate44 via spec.t1.
SUBDIRECTORY outprdt
out1, out2 etc.: The normalised output files for each model.
com.dat: The normalised output file containing the committee results. It is generated by gencom.for.

Detailed instructions on the use of the program are given in the README files. Further information about this suite of programs can be obtained from reference 1.

Top | Next | Prev

References

D.J.C. MacKay, 1997, Mathematical Modelling of Weld Phenomena 3, eds. H. Cerjak & H.K.D.H. Bhadeshia, Inst. of Materials, London, pp 359.
D.J.C MacKay's website at https://www.inference.phy.cam.ac.uk/mackay/

Top | Next | Prev

Parameters

Input parameters

The input variables for the model are listed in the README or README.DOC file in the corresponding directory. The maximum and minimum values for each variable are given in the file MINMAX.