Databases Reference
In-Depth Information
Fig. 4.1.
Metal design optimization.
The predicted properties can be used as objectives in optimal metal design.
In this study, the emphasis is on impact toughness and tensile strength-
based alloy design. Fuzzy models for impact toughness prediction are
used to support the optimization process for multi-objective approaches.
PSO is used as the optimization mechanism for alloy design. This chapter
combines two challenging problems — impact toughness prediction and
multi-objective optimization — into a unified framework and provides a
case study example for multi-objective industrial design problems.
4.3. Neurofuzzy Modeling for Mechanical Property Prediction
Fuzzy modeling is one of the most active research fields in fuzzy logic
systems. Compared with mathematical modeling and neural network
modeling, fuzzy modeling possesses some distinctive advantages, such as
the facility for explicit knowledge representation in the form of if-then rules
(the mechanism of reasoning in human-understandable terms), the capacity
for taking linguistic information from human experts and combining it
with numerical data, and the ability to approximate complicated non-
linear functions with simpler models. Also, the rapid development of hybrid
approaches based on fuzzy logic, neural networks and genetic algorithms has
enhanced fuzzy modeling technology significantly.
A variety of different fuzzy modeling approaches have been developed
and applied in engineering practice.
27-31
The approaches provide powerful
tools for solving complex non-linear system modeling and control problems.
