TY - JOUR ID - 59743 TI - Prediction of Concrete Properties Using Multiple Linear Regression and Artificial Neural Network JO - Journal of Soft Computing in Civil Engineering JA - SCCE LA - en SN - AU - Charhate, Shrikant AU - Subhedar, Mansi AU - Adsul, Nilam AD - Professor, Pillai HOC College of Engineering & Technology, Rasayani, Maharashtra, India AD - Associate Professor, Pillai HOC College of Engineering & Technology, Rasayani, Maharashtra, India AD - Lecturer, Pillai HOC College of Engineering & Technology, Rasayani, Maharashtra, India Y1 - 2018 PY - 2018 VL - 2 IS - 3 SP - 27 EP - 38 KW - Slump KW - Compressive strength KW - Multiple linear regression KW - Artificial Neural Network DO - 10.22115/scce.2018.112140.1041 N2 - The selection of appropriate type and grade of concrete for a particular application is the critical step in any construction project. Workability and compressive strength are the two significant parameters that need special attention. This study aims to predict the slump along with 7-days & 28-days compressive strength based on the data collected from various RMC plants. There are many studies reported in general to address this issue from time to time over a long period. However, considering the worldwide use of a huge quantity of concrete for various infrastructure projects, there is a scope for the study that leads to most accurate estimate. Here, data from various concrete mixing plants and ongoing construction sites was collected for M20, M25, M30, M35, M40, M45, M50, M55, M60 and M70 grade of concrete. Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) models were built to predict slump as well as 7-days and 28-days compressive strength. A variety of experiments was carried out that suggests ANN performs better and yields more accurate prediction compared to MLR model for both slump & compressive strength. UR - https://www.jsoftcivil.com/article_59743.html L1 - https://www.jsoftcivil.com/article_59743_dca6a53758464c6a1cca03d937cbf566.pdf ER -