MAP Logo

Materials Algorithms Project
Neural Networks: Programs Library

[A logo showing the University of Cambridge Crest]


This library contains complete PROGRAMS for the investigation of problems analysed by neural networks.

Format of documentation within this library.

[A][B][C][D] [E][F][G][H] [IJ][K][L][M] [N][O][PQ][R] [S][T][UVW][XYZ]

Programs Available

A

MAP_NEURAL_ADI_HARDNESS
Estimation of the Vickers hardness of austempered ductile cast irons (ADI) as a function of chemical composition and heat treatment conditions (austenitising temperature, austenitising time, austempering temperature and austempering time).
Language: FORTRAN, C & Executable files

MAP_NEURAL_ADI_RETAINED-AUSTENITE
Estimation of the amount of retained austenite in austempered ductile cast irons (ADI) as a function of chemical composition and heat treatment conditions (austenitising temperature, austenitising time, austempering temperature and austempering time).
Language: FORTRAN, C & Executable files

[Top]

B

MAP_ NEURAL_BAINITEPLATE_THICKNESS
Estimates the bainite plate thickness of low-alloy steels as a function of transformation temperature, the chemical free energy available for nucleation and the strength of austenite at the transformation temperature over a limited range of inputs.
Language: FORTRAN

[Top]

C

MAP_NEURAL_CREEP
Estimates the creep rupture strength of ferritic steels, as a function of chemical composition, heat treatment temperature and time.
Language: FORTRAN, C & Executable files

[Top]

D

[Top]

E

[Top]

F

MAP_NEURAL_FECO_LOSSES
Estimation of the losses in FeCo alloys as a function of the temperature, frequency of applied field, and ageing time/temperature.
Language: FORTRAN, C & Executable files

MAP_NEURAL_FERRITE_NUMBER
To predict the ferrite number of austenitic steel welds.
Language: FORTRAN, C & Executable files

[Top]

G

MAP_NEURAL_GENETIC_ALGORITHM
An application of the genetic algorithm (GA) for reaching a solution given a fitting function. This can in theory be applied to any problem, where a database of inputs and outputs has trained a neural network.
Language: C & Executable files

[Top]

H

MAP_NEURAL_HOT_TORSION
To estimate hot torsion stress-strain curves in iron alloys as a function of testing temperature, strain rate, interpass time, chemical composition, strain and the highest strain experienced during previous test.
Language: FORTRAN, C & Executable files

[Top]

IJ

[Top]

K

[Top]

L

MAP_NEURAL_LATTICE_PARAMETER_DATA
Neural Experimental ata for the lattice parameters of austenite and ferrite.
Language: Text

MAP_NEURAL_LATTICE_PARAMETER_AUSTENITE
Neural Network model of data for lattice parameter of austenite.
Language: C, FORTRAN, Executables

MAP_NEURAL_LATTICE_PARAMETER_FERRITE
Neural Network model of data for lattice parameter of ferrite.
Language: C, FORTRAN, Executables

MAP_NICKEL_LATTICE
Calculation of the Gamma and Gamma-prime lattice parameters in nickel base superalloys as a function of the chemical composition and temperature. Based on a neural network model. This program has the alias MAP_NEURAL_LATTICE
Language: C, FORTRAN, Executables

[Back to top]

M

MAP_NEURAL_MA-STEEL
Predicts the yield strength, ultimate tensile strength and elongation of the mechanically alloyed oxide dispersion strengthened (MA-ODS) ferritic stainless steels as a non-linear function of the important processing and service variables.
Language: FORTRAN

[Top]

N

MAP_NEURAL_NNWORK
MS-DOS based neural network program and data files which can be used for predicting cetain weld parameters: the heat affected zone hardness, the 800 to 500 cooling time, t8/5, and the weld dimensions.
Language: Executable program only.

[Top]

O

[Top]

PQ

MAP_NEURAL_PEARLITE_GROWTH
Isothermal austenite-to-pearlite transformation modelled using a neural network technique within a Bayesian 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.
Language: FORTRAN/C

MAP_NEURAL_PEARLITE_SPACING
Estimates the interlamellar spacing of pearlite, using a neural network, as a function of Mn, Cr, Ni, Si and Mo alloying contents and temperature.
Language: FORTRAN/C

MAP_NEURAL_PLUTONIUM
T Neural Network model of data for lattice parameter of delta plutonium.
Language: FORTRAN, C & Executable files

[Top]

R

[Top]

S

MAP_NEURAL_STEEL
Predicts the Ac1 and Ac3 temperatures of steel as functions of the chemical compositions and the heating rate.
Language: FORTRAN

[Top]

T

[Top]

UVW

MAP_NEURAL_WELDMETAL_ELN_CHP
Estimates the tensile elongation and Charpy toughness of steel weldmetal (manual metal arc or submerged arc or tungsten inert gas), as a function of chemical composition, heat input, interpass temperature, post weld heat treatment temperature and time.
Language: FORTRAN, C & Executable files

MAP_NEURAL_WELDMETAL_EMB
To estimate the temper embrittlement of a limited range of ferritic steel welds as a function of silicon, manganese, phosphorus, tin, anitmony and arsenic. Follows the work of Bruscato.
Language: FORTRAN, C & Executable files

MAP_NEURAL_WELDMETAL_T_27J
To estimate the 27 J Charpy impact transistion temperature for ferritic steel welds as a function of the yield strength, oxygen content, reheated material and percentage acicular ferrite.
Language: FORTRAN, C & Executable files

MAP_NEURAL_WELDMETAL_YS_UTS
Estimates the yield strength and ultimate tensile strength of steel weldmetal (manual metal arc or submerged arc or tungsten inert gas), as a function of chemical composition, heat input, interpass temperature, post weld heat treatment temperature and time.
Language: FORTRAN, C & Executable files

MAP_NEURAL_WELD_TOUGHNESS
Estimates the Charpy toughness of steel welds (manual metal arc or submerged arc), as a function of strength, microstructure, chemical composition and temperature over a limited range of inputs.
Language: FORTRAN

[Top]

XYZ

[Top]