Compressive strength prediction of rice husk ash using multiphysics genetic expression programming

• DOI: 10.1016/j.asej.2021.09.020
• Publication Date: 2021-10-06T00:20:13Z
• Authors: Fahid Aslam; Mohamed Abdelghan...; Ammar Iqtidar; Mohsin Ali Khan; Muhmmad Faisal Javed; Kseniia Iurevna U...; M. Ijaz Khan; Sagr Alamri; Muhammad Ali Musarat
• Keywords: Rice hulls; Artificial intelligence; Concrete -- Additives; Multiphysics Models; RHA; Rice -- Residues; 0211 other engineering and technologies; 02 engineering and technology; Engineering (General). Civil engineering (General); GEP; Regression Models; Machine Learning; Regression analysis -- Computer programs; Artificial Intelligence; Machine learning; TA1-2040

Rice husk ash (RHA) is obtained by burning rice husks. An advanced programming technique known as genetic expression programming (GEP) is used in this research for developing an empirical multiphysics model for predicting the compressive strength of RHA incorporated concrete. A vast database comprising of 250 data points is obtained from the extensive and consistent literature review. Different parameters such as age, RHA content, cement content, water content, amount of superplasticizer and aggregate content are used as inputs. A closed-form equation solution was obtained to predict the compressive strength of RHA based on input parameters. The performance of GEP is evaluated by comparing it with regression models. Statistical parameter R2 is used to assess the results predicted by GEP and regression models. Statistical and parametric analysis is also carried out to determine the influence of inputs on the outcome. The GEP model performed better in all terms as compared to other models.