International Journal on Advanced Science, Engineering and Information Technology, Vol. 12 (2022) No. 6, pages: 2421-2427, DOI:10.18517/ijaseit.12.6.16158

Tonne Kilometre Per Hour (TKPH) Prediction for Lifetime Tire Estimate Using Statistical Analysis: A Case Study at Coal Mine

Laura Puspita Sari, Franklin Chandra Pragnyono Seto


To expedite mining production activities, the condition of the transportation equipment of fuel and spare parts must be ready because the loss of time due to refueling and waiting for spare parts can reduce the Physical Availability value of the dump truck. In this study, the type of tire used as the research object is a tire measuring 33.00-51. The initial identification of tire conditions showed that the Hours meter average was smaller than the Key Performance Indicator (KPI) Hours meter, which was 2719 HM. The type of tire damage that dominates is Sidewall Separation, with a damage percentage of 54%. This study aims to predict the value of TKPH with ten independent variables that exist in the activity of the transportation cycle. The method used to predict is the Multiple Regression and ARIMA statistical methods. From the results of Multiple Regression using the SPSS application, three models are produced, each with different independent variables. As for ARIMA seen from the choleogram of the Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF), the number of lags = 1, so ARIMA models that can be applied may be (1,0,1) and (1,1,0). The results of the study prove that the prediction model that is close to this is the Multiple Regression Model 3 where the Mean Absolute Deviation (MAD) value is 69.16, the Mean Absolute Prediction Error (MAPE) is 66.07, and the R-square value is 52.41%.


Tire; TKPH; KPI; multiple regression; ARIMA.

Viewed: 93 times (since abstract online)

cite this paper     download