Premium
Parameter Identification Based on First Order Approximation Neural Networks
Author(s) -
Pichler Bernhard,
Mang Herbert A.
Publication year - 2003
Publication title -
pamm
Language(s) - English
Resource type - Journals
ISSN - 1617-7061
DOI - 10.1002/pamm.200310204
Subject(s) - artificial neural network , a priori and a posteriori , backpropagation , identification (biology) , set (abstract data type) , computer science , algorithm , inverse problem , inverse , mathematics , mathematical optimization , artificial intelligence , mathematical analysis , philosophy , botany , geometry , epistemology , biology , programming language
Abstract Constitutive models for structural analyses contain material parameters. Usually not all of them can be determined a priori with sufficient accuracy. They must be set such that numerical results agree with available measurements as well as possible. Hence, an inverse problem must be solved. In order to keep the number of the required numerical calculations for parameter identification as small as possible, back analyses are performed iteratively. In each iteration step, a backpropagation artificial neural network (BPANN) is trained to approximate results of already performed numerical analyses. In this paper the classical zero‐order training algorithm is extended in order to obtain first‐order approximation neural networks. Based on the trained BPANN, a prognosis of optimal parameters can be obtained.