Open AccessApplication of Multiple Linear Regression Models and Adaptive Neuro-Fuzzy Inference System Models to estimate the Compressive Strength of Concrete
Author(s) -
Mohammed Hussain,
Y. Kamala Raju,
Prasad V Kamakshi
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1126/1/012062
Subject(s) - adaptive neuro fuzzy inference system , compressive strength , linear regression , nonlinear system , sensitivity (control systems) , computer science , neuro fuzzy , regression analysis , mathematics , fuzzy logic , machine learning , artificial intelligence , engineering , materials science , fuzzy control system , physics , quantum mechanics , electronic engineering , composite material
The most widely used composite construction material is concrete. Compressive strength is an important monitoring parameter for quality assurance at construction site. In this paper,two different models of Multiple Linear Regression ( MLR) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are developed to predict the 28 day compressive strength of concrete using the experimental datasets available . These two models are compared . Sensitivity Analysis (SA) is carried out for two different sets of parameters. ANFIS models predict more effectively as their coefficients of multiple determination(R Square) are higher than those of MLR models. This shows that the nonlinear correlation among input variables is better represented in ANFIS models than in MLR models .Goal 12 of United Nations Sustainable Development deals with the sustainable consumption and production patterns and it is taken into account as environmentally degrading materials( flyash and blast furnace slag ) are used.