The Use of a Machine Learning Method to Predict the Real-Time Link Travel Time of Open-Pit Trucks

• DOI: 10.1155/2018/4368045
• Publication Date: 2018-04-19T23:31:53Z
• Authors: Xiaoyu Sun; Hang Zhang; Fengliang Tian; Lei Yang
• Keywords: Link (geometry); Open Pit Mining

Accurate truck travel time prediction (TTP) is one of the critical factors in dynamic optimal dispatch open-pit mines. This study divides roads mines into two types: fixed and temporary link roads. The experiment uses data obtained from Fushun West Open-pit Mine (FWOM) to train three types machine learning (ML) models based on <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M1"><mml:mrow><mml:mi>k</mml:mi></mml:mrow></mml:math>-nearest neighbors (kNN), support vector (SVM), random forest (RF) algorithms for each road. results show that TTP SVM RF are better than kNN. accuracy calculated this approximately 15.79% higher by traditional methods. Meteorological features added model improved 5.13%. Moreover, rather route as minimum unit, former shows an increase 11.82%.