Predicting compressive strength of geopolymer concrete using machine learning

• DOI: 10.1142/s2737599423500032
• Publication Date: 2023-05-10T05:16:44Z
• Authors: Priyanka Gupta; Nakul Gupta; Kuldeep K. Saxena
• Keywords: Python

The anaconda software required python code in order to run the utilized individual K-nearest neighbor (KNN), random forest regression (RFR), and linear (LR) models. results show that RFR machine learning (ML) technique out of other models shows best performance for a used dataset. findings this article indicate dataset proposed model provides an acceptable algorithm FACC design optimization. In current study preparation geopolymer concrete (GPC), relevant variables such as curing, fly ash, calcined clay, added water, super plasticizer, coarse aggregate, quarry stone dust, caustic soda, water glass were input parameters. ranges, mode, median, standard deviation, identifying details checked using descriptive statistical analysis strength due compression GPC was predicted RFR, LR, KNN ML techniques, all based on Python coding. ensemble technique, outperformed KNN, terms prediction. indicates maximum amount [Formula: see text] is 0.92, LR 0.58, although less accurate, with coefficient determination 0.56. technique’s lower values errors, mean absolute error (MAE), MSE, root square (RMSE) yield 1.99, 7.17, 2.67[Formula: text]MPa, respectively. excellent accuracy methodology confirmed by errors. Curing temperature, curing hours, molarity NaOH, ratio significantly affect compressive (CS) GPC. optimization among three combinations methods given