A Self-Adaptive Fuzzy Inference Model Based on Least Squares SVM for Estimating Compressive Strength of Rubberized Concrete

摘要

This paper presents an AI approach named as self-Adaptive fuzzy least squares support vector machines inference model (SFLSIM) for predicting compressive strength of rubberized concrete. The SFLSIM consists of a fuzzification process for converting crisp input data into membership grades and an inference engine which is constructed based on least squares support vector machines (LS-SVM). Moreover, the proposed inference model integrates differential evolution (DE) to adaptively search for the most appropriate profiles of fuzzy membership functions (MFs) as well as the LS-SVM's tuning parameters. In this study, 70 concrete mix samples are utilized to train and test the SFLSIM. According to experimental results, the SFLSIM can achieve a comparatively low MAPE which is less than 2%.