Taguchi's method for multi-objective optimization problems

Abstract

Taguchi's method is a quality design technique whose applications in numerical single-objective optimization have been recently exploited. In this article, a novel multiobjective (MO) algorithm based on Taguchi's technique is illustrated and its performances assessed. Validation is performed through a comparison between the presented algorithm and a MO genetic algorithm (GA) based optimization, first on different sets of test functions and then on a practical antenna array synthesis problem. Results indicate a generally better behavior of the proposed algorithm in terms of convergence and spreading over the Pareto front with respect to the GA benchmark.

A Novel Multiobjective Taguchi's Optimization Technique for Multibeam Array Synthesis

“…It is well known that deterministic methods are likely to fall in local minima, and that their effectiveness can depend on the search starting point. Stochastic methods on the other hand have very good global search capabilities, hence random (R) and semi‐random (S) variants of the original deterministic (D) TM have been proposed , which avoid local minima at the cost of a modest increase in the number of iterations.…”

“…Among stochastic techniques, both genetic algorithms (GA) and particle swarm optimization (PSO) have been extended to MO and applied to arrays . In this article, a recently developed multiobjective technique based on Taguchi's method (MO‐TM) will be applied to the design of multibeam linear arrays.…”

Quasi‐elliptical band‐pass filters based on compact spiral resonators for C‐band applications

“…Exploiting the parametric analysis in Section 2.2, it is quite easy to design a filter centered at the desired operation frequency. Furthermore, with the latter addition of interconnecting lines, the set of parameters is adequate to perform a final tuning with a multiobjective optimization …”

A Circularly Polarized Antenna for Dual Band Operation at 2.45 GHZ and 5.10 GHZ

“…Given the large number of constraints at the two frequencies of operation, a dedicated multi-objective approach for optimization, operating on concurrent parameters, has been carried out, following the strategy introduced in [23,24] and further refined in [25].…”