Search

When solving multi-objective optimization problems subject to constraints in reliability-based design, it is desirable for the decision maker to have a sufficient number of solutions available for selection. However, many existing approaches either combine multiple objectives into a single objective or treat the objectives as penalties. This results in fewer optimal solutions than would be provided by a multi-objective approach. For such cases, a niched Pareto Genetic Algorithm (GA) may be a viable alternative. Unfortunately, it is often difficult to set penalty parameters that are required in these algorithms. In this paper, a multi-objective optimization algorithm is proposed that combines a niched Pareto GA with a constraint handling method that does not need penalty parameters. The proposed algorithm is based on Pareto tournament and equivalence sharing, and involves the following components: search for feasible solutions, selection of non-dominated solutions and maintenance of diversified solutions. It deals with multiple objectives by incorporating the concept of Pareto dominance in its selection operator while applying a niching pressure to spread the population along the Pareto frontier. To demonstrate the performance of the proposed algorithm, a test problem is presented and the solution distributions in three different generations of the algorithm are illustrated. The optimal solutions obtained with the proposed algorithm for a practical reliability problem are compared with those obtained by a single-objective optimization method, a multi-objective GA method, and a hybrid GA method. [ABSTRACT FROM AUTHOR]

In most practical situations involving reliability optimization, there are several mutually conflicting goals such as maximizing the system reliability and minimizing the cost, weight and volume. This paper develops an effective multiobjective optimization method, the Intelligent Interactive Multiobjective Optimization Method (IIMOM). In IIMOM, the general concept of the model parameter vector is proposed. From a practical point of view, a designer's preference structure model is built using Artificial Neural Networks (ANNs) with the model parameter vector as the input and the preference information articulated by the designer over representative samples from the Pareto frontier as the desired output. Then with the ANN model of the designer's preference structure as the objective, an optimization problem is solved to search for improved solutions and guide the interactive optimization process intelligently. IIMOM is applied to the reliability optimization problem of a multi-stage mixed system with five different value functions simulating the designer in the solution evaluation process. The results illustrate that IIMOM is effective in capturing different kinds of preference structures of the designer, and it provides a complete and effective solution for medium- and small-scale multiobjective optimization problems. [ABSTRACT FROM AUTHOR]