Affiliations: President Office, Hebei Institute of Architectural Science and Technology, Handan, Hebei, 056038 P.R. China, e‐mail: [email protected] | Institute for Reinforced and Prestressed Concrete Structures, Ruhr‐University Bochum, Girondelle 78b, Haus 5, 44799 Bochum, Germany | Beijing Dacheng Real Estimate Development Corporation, No. 28 West Street of Xuan‐Wu‐Men, Xuan‐Wu District, Beijing, 100053 P.R. China
Abstract: It is a complex non‐linear problem to predict mechanical properties of concrete. As a new approach, the artificial neural networks can extract rules from data, but have difficulties with convergence by the traditional algorithms. The authors defined a new convex function of the grand total error and deduced a global optimization back‐propagation algorithm (GOBPA), which can solve the local minimum problem. For weights' adjustment and errors' computation of the neurons in various layers, a set of formulae are obtained by optimizing the grand total error function over a simple output space instead of a complicated weight space. Concrete strength simulated by neural networks accords with the data of the experiments on concrete, which demonstrates that this method is applicable to concrete properties' prediction meeting the required precision. Computation results show that GOBPA performs better than a linear regression analysis.
Keywords: data processing, neural networks, global optimization algorithm, properties of concrete
Journal: Informatica, vol. 14, no. 1, pp. 95-110, 2003
