Authors:
Pedro Henrique Gouvea Coelho
;
J. F. M. do Amaral
and
M. C. Bentes
Affiliation:
State Univ. of Rio de Janeiro, FEN/DETEL, R. S. Francisco Xavier, 524/Sala 5001E, Maracanã, R. J., 20550-900, Brazil
Keyword(s):
Genetic Algorithms, Artificial Intelligence Applications, Evolutionary Electronics.
Abstract:
This paper presents an electronic circuit evolution platform based on genetic algorithms with different modes of operation. The platform has an extrinsic structure for evaluating individuals, making calls to a circuit simulator for each possible solution evaluated. The platform can perform evolutions in search of values for components, additional topologies to a fixed circuit and a search with total variation in the types of components, values and connections. The assessed fitness can be based on a single objective, evaluating only the output of the circuit, but also based on several objectives. The chosen method for this quantification of multiple objectives is based on a Fuzzy System in order to facilitate the designer's specification. The evolutions can be carried out in the time domain as well as in the frequency domain, being possible for the user to change the operating mode without changes in the code already created. The exchange between the operating modes, inputs used and t
he use of functions present on the platform is performed directly through configuration variables, without the need to change the source code of the platform. In order to verify the performance of the platform, each mode can be evaluated using different circuits with varying complexities. Some selected case studies are shown in the paper to corroborate the feasibility of the method.
(More)