Purpose - The purpose of this paper is to present a constructive algorithm to design multilayer perceptron neural networks used as approximation models of electromagnetic devices. Design/methodology/approach - The proposed procedure allows automatic determination of both the number of neurons and the synaptic weights of networks with a single hidden layer. The approximation model is used in design optimization problems. The inputs of the neural network correspond to the design parameters whereas the output corresponds to the objective function of the optimization problem. The neural model is then inverted in order to determine which input is associated to a prefixed output. Findings - The performance of the algorithm has been tested on analytical function and on the TEAM workshop problem 25. Originality/value - As the reliability of the optimum solution is strongly affected by the accuracy of the neural approximation model, the approximation error is kept as low as possible, especially in the maximum/minimum points.
A constructive algorithm of neural approximation models for optimization problems
CARCANGIU, SARA;FANNI, ALESSANDRA;MONTISCI, AUGUSTO
2009-01-01
Abstract
Purpose - The purpose of this paper is to present a constructive algorithm to design multilayer perceptron neural networks used as approximation models of electromagnetic devices. Design/methodology/approach - The proposed procedure allows automatic determination of both the number of neurons and the synaptic weights of networks with a single hidden layer. The approximation model is used in design optimization problems. The inputs of the neural network correspond to the design parameters whereas the output corresponds to the objective function of the optimization problem. The neural model is then inverted in order to determine which input is associated to a prefixed output. Findings - The performance of the algorithm has been tested on analytical function and on the TEAM workshop problem 25. Originality/value - As the reliability of the optimum solution is strongly affected by the accuracy of the neural approximation model, the approximation error is kept as low as possible, especially in the maximum/minimum points.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.