Application of artificial neural network in materials research

1

• Application of artificial neural network in
  materials research
• Wei SHA
• Professor of Materials Science
• http//space.qub.ac.uk8077/cber/Sha
• 25 June 2007

2
Modelling methodologiesMetals Research Group,
Queens University

1. Thermodynamic modelling
2. The Johnson-Mehl-Avrami method and its adaption
   to continuous cooling and heating
3. Finite element method
4. Phase field method
5. Atomistic simulation
6. Neural network method

3
The modelsIntegrated
Malinov, Sha, JOM, 57(11), 2005, 54.
4
The modelsGraphical user interfaces of software
for modelling
Composition-processing-temperature-mechanical
properties TTT diagrams
Fatigue life CCT diagrams Microhardness
profile
Malinov, Sha, Computational Materials Science,
28, 2003, 179.
5
Basic principles of neural network
modellingNatual Artificial
Neuron
Neural Network
The human brain contains 1010 1011 neurons
Malinov, Sha, McKeown, Computational Materials
Science, 21, 2001, 375.
6
Basic principles of neural network
modellingArchitecture of the neural network
Malinov, Sha, Guo, Materials Science and
Engineering A, 283, 2000, 1.
7
Basic principles of neural network
modellingNeural network modelling steps

• Database collection
• Analysis and pre-processing of the data
• Design and training of the neural network
• Test of the trained network
• Using the trained NN for simulation and prediction

8
Database construction and analysisTraining
database
9
Database construction and analysisDistribution
of the input dataset
Guo, Malinov, Sha, Computational Materials
Science, 32, 2005, 1.
10
Algorithm of computer programCreation of neural
network model
11
Algorithm of computer programSteps in creating
the model
McBride, Malinov, Sha, Materials Science and
Engineering A, 384, 2004, 129.
12
Algorithm of computer program Post-training
linear regression analysis
13
Algorithm of computer program Training parameters
14
Algorithm of computer program Post-training
validation of the software simulations
400
Min - 37.94 Max 35.89 Mean -0.13 STDEV
10.31
350
300
250
200
Number
150
100
50
0
-40
-30
-20
-10
0
10
20
30
40
15
Algorithm of computer program Comparison between
prediction and experiments
Sha, JOM, 58(9), 2006, 64.
16
Noise tolerance The experimental values are
values including noise
17
Noise tolerance The experimental values are
values without noise
18
Use of the softwareBlock diagram of software
system for modelling
19
Use of the software Influence of alloy
composition in g-TiAl, 1040 C
Malinov, Sha, Materials Science and Engineering
A, 365, 2004, 202.
20
Use of the software Microhardness profiles of
titanium after nitriding
Zhecheva, Malinov, Sha, JOM, 59(6), 2007, 38.
21
Use of the software Ti15Mo5Zr3Al, nitrided in
N2 at 750 C for 60 h
Zhecheva, Malinov, Sha, Surface and Coatings
Technology, 200, 2005, 2332.
22
Use of the softwareOptimization of the alloy
composition processing
http//space.qub.ac.uk8077/cber/Sha