Prediction of compressive strength of cementitious grouts for semi-flexible pavement application using machine learning approach

• DOI: 10.1016/j.cscm.2023.e02370
• Publication Date: 2023-08-06T01:02:13Z
• Authors: Muhammad Imran Khan; Nasir Khan; Syed Roshan Zamir...; Muhamad Razuhanaf...; Nur Izzi Md Yusoff; Rai Waqas Azfar; Mujahid Ali; Roman Fediuk
• Keywords: Superplasticizer; Grout; Cementitious; Water–cement ratio

This study involves the preparation of cement grout samples by varying proportions superplasticizer (SP) and water-cement (w/c) ratio (0.25-0.45) which were tested for computing flow value 1-day, 7-day, 28-day compressive strength. With 75 data points a neural network model was developed to predict strength based on w/c ratio, percentage, value, strengths 1-day 7-day as input variables. Due better performance Artificial Neural Networks (ANN) over other applied models, this predicts confident pattern relationship between (indirect), (direct up 3%), corresponding characteristics samples. The prediction power has been improved from R2 =0.959 =0.984 optimizing number neurons, activation function, optimizer. best observed in case Model45-R_A. same used assessing effect percentage water 28 days where 73.941 MPa recorded 3% 0.25.