Title: Appraisal of artificial intelligence techniques for the prediction of on-site dump truck tyre operating hours

Authors: Solomon Evans Kweku Koomson; Victor Amoako Temeng; Yao Yevenyo Ziggah

Addresses: Department of Mining Engineering, Faculty of Mining and Minerals Technology, University of Mines and Technology, Ghana ' Department of Mining Engineering, Faculty of Mining and Minerals Technology, University of Mines and Technology, Ghana ' Department of Geomatic Engineering, Faculty of Geosciences and Environmental Studies, University of Mines and Technology, Ghana

Abstract: Accurate prediction of on-site dump truck tyre operating hours in the mines is an important measure to consider in the transportation management system of trucks to achieve the desired materials production targets and reduction in both operational cost and truck downtimes. This study is focused on predicting dump truck tyre operating hours which is also an important tool in estimating the lifespan of the tyre in mining operations. This paper for the first time appraised the prediction efficiency of backpropagation neural network (BPNN), support vector machine (SVM), radial basis function neural network (RBFNN), group method of data handling (GMDH) and multivariate adaptive regression splines (MARS) for the on-site dump truck tyre operating hours. The overall statistical analyses showed the emergence of BPNN as the best predictor model by achieving the least MAPE (1.3162%) and AIC (434.7942) with the highest R (0.9982), R² (0.9964), NSE (0.9953) and VAF (99.5429%).

Keywords: materials transportation system; dump truck tyres; on-site tyre operating hours; site controllable parameters; artificial intelligence; mining operation.

DOI: 10.1504/IJMME.2023.133650

International Journal of Mining and Mineral Engineering, 2023 Vol.14 No.2, pp.157 - 179

Received: 29 Aug 2022
Accepted: 14 Jun 2023
Published online: 27 Sep 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article