Multi-objective Optimization Task Research Articles

Multiobjective Optimization of Current Waveforms for Switched Reluctance Motors by Genetic Algorithm

In this article a genetic algorithm (GA) is employed to determine the desired current waveforms for switched reluctance motors (SRM) through generating appropriate reference phase torques for a given desired torque using torque-sharing function. The objective is to yield smoother phase current waveforms in general, and achieve minimum phase current variations in particular. This problem is formulated into a multiobjective optimization task with certain constraints. Due to the highly nonlinear relationship between the SRM torque and current, this optimization task is an NP-hard problem. To deal with the difficulty, the problem is further coded so that a GA can be applied to facilitate the search of global minimum. Simulation results verify the effectiveness of the proposed method.

Multi-objective cooperative coevolution of artificial neural networks (multi-objective cooperative networks)

In this paper we present a cooperative coevolutive model for the evolution of neural network topology and weights, called MOBNET. MOBNET evolves subcomponents that must be combined in order to form a network, instead of whole networks. The problem of assigning credit to the subcomponents is approached as a multi-objective optimization task. The subcomponents in a cooperative coevolutive model must fulfill different criteria to be useful, these criteria usually conflict with each other. The problem of evaluating the fitness on an individual based on many criteria that must be optimized together can be approached as a multi-criteria optimization problems, so the methods from multi-objective optimization offer the most natural way to solve the problem. In this work we show how using several objectives for every subcomponent and evaluating its fitness as a multi-objective optimization problem, the performance of the model is highly competitive. MOBNET is compared with several standard methods of classification and with other neural network models in solving four real-world problems, and it shows the best overall performance of all classification methods applied. It also produces smaller networks when compared to other models. The basic idea underlying MOBNET is extensible to a more general model of coevolutionary computation, as none of its features are exclusive of neural networks design. There are many applications of cooperative coevolution that could benefit from the multi-objective optimization approach proposed in this paper.

PERFORMANCE AND ROBUSTNESS DESIGN OF CONTROL SYSTEMS VIA GENETIC-SEX MULTI-OBJECTIVE OPTIMIZATION

Abstract. In this paper new evolutionary method of solving multi-objective optimization problems is presented. This method utilizes an information about an individual sex for the purpose of distinction between different groups of objectives. In particular, this information is extracted from the fitness of individuals and applied during the parental crossovers in a multi-objective optimization process. Characteristics of this mechanism are discussed and its performance in an exemplary multi-objective PID control optimization task is presented.

Hybridization of a multi-objective genetic algorithm, a neural network and a classical optimizer for a complex design problem in fluid dynamics

This paper describes the combination of several optimization technologies that can be used to tackle challenging design problems. The approach, that uses a multi-objective genetic algorithm, a neural network, and a gradient-based optimizer, is first outlined with the help of a computationally inexpensive mathematical test function. Then the methodology is applied to the design of a sailing yacht fin keel, coupling the optimization codes to 3D Navier–Stokes simulations. To perform the multi-objective optimization task a parallel computer is employed.