A novel evolutionary algorithm for identifying multiple alternative solutions in model updating

This article proposes an evolutionary algorithm that is able to identify both global and local minima. This is accomplished by including two new operators to a traditional steady-state genetic algorithm. The proposed algorithm uses a single population in contrast to other evolutionary algorithms available in the literature. The algorithm is used to update a model of a structural system and provide the analyst with different plausible solutions for the updated models. Model updating techniques are used to enhance the behavior of numerical models of existing structures based on experimental data. Although the optimal updated model corresponds to the global minimum of the objective function, the model with the best physical representation of the structure could be a local minimum because of modeling errors, noise in the experimental data, errors in the extraction of system features from the experimental data and limited number sensors, among other factors. The evolutionary algorithm proposed in this article identifies global and local minima of the objective function, giving the analyst the option to choose the updated model from a set of plausible models. These models are specially designed to be as physically different as possible from each other providing the analyst with significantly different alternatives. The proposed methodology is validated with two numerical examples. The first example shows the capabilities of the technique with a mathematical function. A model updating problem using the American Society of Civil Engineering Structural Health Monitoring Benchmark structure is used for the second numerical example.