비파괴검사 데이터를 이용한 다중 신경망 콘크리트 강도추정 모델의 개발

Abstract

The purpose of this paper is to develop a module of HICons(High-Intelligence-based Diagnosis System for Concrete Structure) that can provide in-place strength information of the concrete to facilitate concrete form removal and quality control of concrete structure. For this purpose, the system is developed with artificial neural networks (ANN) that can learn cylinder test and non-destructive test results using Impact-echo method and SASW(Spectral analysis of surface wave method) as training patterns. The concrete strength prediction module is classified into ANN-I and ANN-II. ANN-I predicts concrete strength based on basic information, material properties, measurement and temperature & humidity history from pouring day to 28th day after pouring. ANN-II predicts concrete strength based on additionally non-destructive test data. In the simulation results of ANN-II show higher accuracy than that of ANN-I.