Publication Date:
2018-01-27
Description:
One of the state-of-the-art optimization strategies is the introduction of an artificial neural network in place of a more time-consuming numerical tool to compute the cost function. This work describes the development of a genetic algorithm optimization strategy for a meandered microstrip line by using an artificial neural network whose training set has been designed by a uniform sampling of the global design space. The results in terms of the total radiated electromagnetic power are discussed and compared with those obtained by the initial and not optimized configuration.
Print ISSN:
0018-9375
Electronic ISSN:
1558-187X
Topics:
Electrical Engineering, Measurement and Control Technology