Title: Artificial Neural Networks: An Alternative Approach to Risk Based Design
1Artificial Neural Networks An Alternative
Approach toRisk Based Design
By George Mermiris
2Introduction
- Inspiration from the study of the human brain and
physical neurons - Response speed for physical neurons is 10-3 s
compared to electrical circuits with 10-9 s - Massive parallel structure 1011 neurons with 104
connections per neuron - The efficiency of the brain is directly dependent
on the accumulated experience ? new connections
are established which determine our capabilities
3The Biological Model
4Artificial Neural Networks (ANN)Basic Forms,
Feed-Forward Networks
General pattern
- p input vector
- w weight matrix
- b bias vector
- n net output of the neuron
- ? activation function
- a output vector of the network
a f(n) f(wp b)
a f(n) f(wp b)
5Multi-Neuron, Single-Layer ANN
a f(n) f(Wp b)
6Multi-Layer, Multi-Neuron Network
7Abbreviated Form of a Network
8Activation Functions
Linear Function
Log Sigmoid Function
Hyperbolic Tangent Sigmoid Function
9Training Neural Networks
- The training of a network has the same concept
as for humans the larger its experience the
better its response - For an ANN the learning is established with
suitable adjustment of its weights and biases - Requirements training data and proper algorithm
10The Backpropagation Algorithm
- A three-fold concept
- Performance Index Approximate Square Error F(x)
(t - a)T(t a) eTe
The Steepest Descent Algorithm for function F and
modifications
g gradient
11The Backpropagation Algorithm
- Calculation of the first derivatives of the
performance index starting from the last layer
and backpropagating to the first (!)
Levenberg Marquardt algorithm Main variation
of the method based on the concept of Newtons
method with small approximation
12Example 1 Resistance Experiment
- Case 1 1 cm wave amplitude
- ANN Architecture
- 1-4-3-1
- Activation Function Log Sigmoid for hidden
layers and Linear for output layer
13Example 1 Resistance Experiment
14Example 1 Resistance Experiment
- Case 2 2 cm wave amplitude
- ANN Architecture
- 1-3-2-1
- Activation Function Log Sigmoid for hidden
layers and Linear for output layer
15Example 1 Resistance Experiment
16Example 2 Section Areas Curve
- Input L, Amax, ?, LCB, Cp
- ANN Architecture 5-10-12-21
- Activation Function Log Sigmoid for hidden
layers and Linear for output layer
17Example 2 Section Areas Curve
- Training Set
- - L153 156 159 180, in m
- - Amax335 345 355 425, in m2
- - ?36000 37000 38000 45000 , in m3
- - LCB-2.4 2.5 2.6 -3.3, in m
- - Cp0.702 0.688 0.660 0.588
- Ordinates of SA curves for each combination
- Generalisation Sets L Amax ? LCB Cp
- - Set1160 360 38500 2.65 0.6664
- - Set2178.5 420 44500 3.25 0.594
- - Set3150 325 35000 2.3 0.718
Network input
Network output
Testing the network
18Example 2 Section Areas Curve (Set1)
19Example 2 Section Areas Curve (Set2)
20Example 2 Section Areas Curve (Set3)
21Strong points of ANN
- Readily applicable to any stage of the design
process, especially at the preliminary design
where rough approximations are necessary - Potential to include different design parameters
in the training set and avoid iterations - Results are obtained very fast with high accuracy
- No highly sophisticated mathematical technique is
involved, only basic concepts of Linear Algebra
and Calculus - Very short computer times in common PCs
22 Weak points of ANN
- Basic requirement is the existence of historical
data for the creation of training set - Not readily applicable to novel ship types
- The results are very sensitive to the networks
architecture and the training method selected
each time, although these two parameters are very
easily adjusted - There is no specific network architecture for a
specific calculation different architectures can
provide the same results. The general rule is to
use the simplest possible network
23Future Work
- Other networks and training algorithms recurrent
ANN
- Suitable database for creating the training set
for different applications
- Application to the Global Ship Design including
Risk Data and Human Reliability Data
24Thank You!