[MAP Logo]

Materials Algorithms Project
Program Library


Subroutine MAP_STEEL_TRIP_AUSTENITE

  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

S Chatterjee, December 2006, sc446@cam.ac.uk
Phase Transformations and Complex Properties Research Group,
Materials Science and Metallurgy,
University of Cambridge,
U.K.

The neural network program was produced by:

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

Top | Next

Purpose

There are two separate programs included.

  1. To predict the amount (vol.%) of retained austenite in TRIP-assisted steels as a function of chemical composition and heat treatment parameters.
  2. To predict the carbon content (wt%) of retained austenite in TRIP-assisted steels as a function of chemical composition and heat treatment parameters.

Top | Next | Prev

Specification

Language: executables, C
Product form: executables

Description

Austenite is retained as only a minor constituent in TRIP-assisted steels. The steels are initially heated at a sufficiently high temperature in order to form an equiproportionate mixture of ferrite and austenite (Intercritical Annealing, IA). The austenite is then allowed to partly transform into bainite by holding the material at a lower temperature (Isothermal Treatment, IT). The untransformed austenite subsequently gets enriched with carbon and hence retained at ambient temperature after cooling. Chemical composition of the steel as well as the temperature and the time at the two stages of heat treatment influence the quantity of retained austenite and its carbon content.

Data used to create the model were collected from references [1-22]. The actual research is described in [23].

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 (details may differ between LINUX and PC versions):

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 or model.exe
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.

Top | Next | Prev

References

  1. De Meyer, M., Vanderschueren, D., De Cooman, B. C., ISIJ International 39 (1999) 813-822
  2. Jacques, P. J., Girault, E., Martens, A., Verlinden, B., Van Humbeeck, J, and Delannay, F., ISIJ International 41 (2001) 1068-1074
  3. Jacques, P. J., Girault, E., Harlet, P. and Delannay, F., ISIJ International 41 (2001) 1061-1067
  4. Chen, H. C., Era, H. and Shimizu, M., Metallurgical and Materials Transactions A 20 (1989) 437-445
  5. Itami, A., Takahashi, M. and Ushioda, K., ISIJ International 35 (1995) 1121-1127
  6. Jacques, P., Furnemont, Q., Mertens, A. and Delannay, F., Philosophical Magazine A 81 (2001) 1789-1812
  7. Jacques, P., Girault, E., Catlin, T., Geerlofs, N., Kop, T., Van der Zwaag, S. and Delannay, F., Materials Science and Engineering A 273-275 (1999) 475-479
  8. Kim, S. J., Lee, C. G., Lee, T. H. and Oh, C. S., ISIJ International 42 (2002) 1452-1456
  9. Kim, S. J., Lee, C. G., Choi, I. and Lee, S., Metallurgical and Materials Transactions A 32 (2001) 505-514
  10. Lee, C. G., Kim, S. J., OH, C. S. and Lee, S., ISIJ International 42 (2002) 1162-1168
  11. Matsumura, O., Sakuma, Y. and Takechi, H., ISIJ International 32 (1992) 1014-1020
  12. Matsumura, O., Sakuma, Y. and Takechi, H., Scripta Metallurgica 27 (1987) 1301-1306
  13. Nakagaito, T., Shimizu, T., Furukimi, O. and Sakata, K., Tetsu-to-Hagane 89 (2003) 841-847
  14. Pichler, A., Stiaszny, P., Potzinger, R., Tikal, R. and Werner, E. 40th Mechanical Working and Steel Processing Conference Proceedings, Iron and Steel Society/AIME, USA 36 (1998) 259-274
  15. Sakuma, Y., Matlock, D. K., Krauss, G., Materials Science and Technology 9 (1993) 718-724
  16. Sakuma, Y., Matsumara, O. and Takechi, H., Metallurgical and Materials Transactions A 22 (1991) 489-498
  17. Traint, S., Pichler, A., Stiaszny, P. and Wemer, E. A., 44th Mechanical Working and Steel Processing Conference Proceedings, Iron and Steel Society/AIME, USA 40 (2002) 139-152
  18. Traint, S., Pichler, A., Tikal, R., Stiaszny, P., Wemer, E. A., 42nd Mechanical Working and Steel Processing Conference Proceedings, Iron and Steel Society/AIME, USA 38 (2000) 549-561
  19. Jacques, P. J., Girault, E., Martens, A., Verlinden, B., Van Humbeeck, J, and Delannay, F., ISIJ International 41 (2001) 1068-1074
  20. Jacques, P. J., Girault, E., Harlet, P. and Delannay, F., ISIJ International 41 (2001) 1061-1067
  21. Wang, Z. C., Kim, S. J., Lee, C. G. and Lee, T. H., Journal of Materials Processing Technology 151 (2004) 141-145
  22. Zaefferer, S., Ohlert, J. and Bleck, W., Acta Materialia52 (2004) 2765-2778
  23. S. Chatterjee, PhD thesis, Cambridge University, 2006.

Top | Next | Prev

Parameters

Program number 1, inputs

Inputs in sequence C, Mn, Si, Al, P, Mo, Cu (all in wt%), IA temperature (degrees Centigrade), IA time (s), IT temperature (degrees Centigrade) and IT time (s). The following example has five sets of inputs.

    
0.2 1.5 1.5 0 0 0 0 780 300 350 60 
0.2 1.5 1.5 0 0 0 0 780 300 350 120 
0.2 1.5 1.5 0 0 0 0 780 300 350 180 
0.2 1.5 1.5 0 0 0 0 780 300 350 240 
0.2 1.5 1.5 0 0 0 0 780 300 350 300

Program number 1, results

Outputs in sequence amount of retained austenite (vol.%), followed by a one sigma modelling uncertainty. The outputs listed below correspond to the inputs described above.

  
5.708427 3.004774
6.364171 2.700870
6.927576 2.493075
7.397646 2.369859
7.774651 2.316240

Program number 2, inputs

Inputs in sequence C, Mn, Si, Al, P, Cu (all in wt%), IA temperature (degrees Centigrade), IA time (s), IT temperature (degrees Centigrade) and IT time (s). The following example has five sets of inputs.

 
0.2 1.5 1.5 0 0 0 780 300 350 60 
0.2 1.5 1.5 0 0 0 780 300 350 120 
0.2 1.5 1.5 0 0 0 780 300 350 180 
0.2 1.5 1.5 0 0 0 780 300 350 240 
0.2 1.5 1.5 0 0 0 780 300 350 300

Program number 2, results

Outputs in sequence carbon content of retained austenite (wt%), followed by a one sigma modelling uncertainty. The outputs listed below correspond to the inputs described above.

  
0.748936 0.138892
0.813325 0.137670
0.868952 0.137088
0.916619 0.137054
0.957145 0.137550

Top | Next | Prev

Auxiliary Routines

None.

Top | Next | Prev

Keywords

neural network, retained austenite, bainite, TRIP-assisted steel

Top | Next | Prev

Download

Download source code, fraction of austenite (Linux)

Download source code, carbon in austenite (Linux)

Download source code, fraction of austenite (PC)

Download source code, carbon in austenite (PC)

Top | Prev

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

Top | MAP Homepage