An efficient approach for cement strength prediction. Issue 1 (2nd January 2023)

• Record Type: Journal Article
• Authors: Gaidhane, Vilas H.; Kumar, Nand; Mittal, Ravi Kant; Rajevenceltha, J.
• Is Part Of: International journal of computers and applications. Volume 45:Issue 1(2023)
• Page Start: 8
• Page End: 18
• Publication Date: 2023-01-02
• Subjects: Cement strength -- polynomial coefficients -- SOM -- regression model -- artificial neural network -- prediction; Computers -- Periodicals; Computer software -- Periodicals; Computer networks -- Periodicals; Multimedia systems -- Periodicals; Internet -- Periodicals; World Wide Web -- Periodicals; Minicomputers -- Periodicals; Microcomputers -- Periodicals; 004.05
• DOI: 10.1080/1206212X.2019.1673288
• Languages: English
• ISSNs: 1206-212X

Abstract

Abstract : In this paper, a simple and computationally efficient approach is proposed to predict the cement strength. It is based on the mathematical concept of covariance matrix and polynomial coefficients. The polynomial coefficients are used to represent the features of cement strength data set. The efficiency and feasibility of the proposed approach is demonstrated on the cement strength data set collected from the cement industry for 2 days, 7 days and 28 days samples. Based on the number of dynamic input variables of the cement strength, the different prediction models such as SOM, linear and nonlinear regression and artificial neural network are designed and the various experimentations are carried to evaluate the proposed approach. Experimental results have shown the effectiveness of the proposed approach in the form of RMSE, R -square coefficients and computational time. It is observed that the proposed polynomial coefficient-artificial neural network approach performs better and predict the cement strength efficiently as compared to other existing methods.