Back analysis of microplane model parameters using soft computing methods

TL;DR

This paper introduces a novel method for identifying microplane model parameters using neural networks trained with genetic algorithms, enhanced by Latin Hypercube Sampling and sensitivity analysis, improving parameter estimation accuracy.

Contribution

It combines Latin Hypercube Sampling, stochastic sensitivity analysis, and genetic algorithms to improve microplane model parameter identification with neural networks.

Findings

Effective neural network training with genetic algorithms

Enhanced parameter identification accuracy

Discussion of method advantages and limitations

Abstract

A new procedure based on layered feed-forward neural networks for the microplane material model parameters identification is proposed in the present paper. Novelties are usage of the Latin Hypercube Sampling method for the generation of training sets, a systematic employment of stochastic sensitivity analysis and a genetic algorithm-based training of a neural network by an evolutionary algorithm. Advantages and disadvantages of this approach together with possible extensions are thoroughly discussed and analyzed.