Predicting tensile strength of cemented paste backfill with aid of second order polynomial regression

Abstract

The materials left behind after the process of separating an ore's valuable fraction from the unprofitable fraction are known as tailings in the mining industry. Mixing tailing, cement and water can create a new material called Cemented paste backfill (CPB). Research and solve the problem of predicting the tensile strength of cement paste backfill based on a polynomial model combined with the Monte Carlo Simulation method. Three models were built to evaluate performance. The optimal performance model is then used to predict the tensile strength of cement paste backfill. The results indicate that using the polynomial regression model has a satisfactory result for predicting the tensile strength of cement paste backfill. The best performance of second order polynomial regression model is evaluated by three metrics such as R²=0.958 RMSE=33.211 kPa MAE=29.097 kPa for testing part in predicting the tensile strength of cemented paste backfill. Finally, the influence of Cement/Tailings ratio and Solid content on the tensile strength on tensile strength and importance is also evaluated with aid of the best performance of second order polynomial regression model.