To obtain optimal design efficiently in the initial
design stage of a ship, a hybrid system is developed by
integrating the optimization algorithm and knowledge-based
system. The hybrid system can manipulate numeric and symbolic
data simultaneously. To increase search efficiency in a
design space, the optimization algorithm (optimizer) is
implemented by coupling a genetic algorithm (GA) and search
method. The optimizer determines a candidate region around
the optimum point by using the GA, then searches the optimum
point by the search method concentrating in this region,
thus reducing calculation time and increasing search efficiency.
To generate input data for the optimizer, a rule-based
system is developed. Some domain knowledge for ship optimization
in the initial design stage is retrieved from a database
of existing ship and design experts. The obtained knowledge
is stored in the knowledge base. The optimizer incorporates
a knowledge-based system with heuristic and analytic knowledge,
thereby narrowing the feasible space of the design variables.
Therefore, search speed and the capability of finding an
optimum point will be increased in comparison with conventional
approach. The developed system is applied principally to
particulars of optimization of ships with multicriteria.
Through application ship design, it shows that the hybrid
system can be a useful tool for optimum design.