Artificial intelligence approach to calculation of hydraulic excavator cycle time and output

摘要: AbstractAccurate prediction of the cycle time and output tracked hydraulic excavators is notoriously difficult, not least because such data are freely available to mining practitioner from only a limited number plant manufacturers. Previous research attempted rectify this problem through development ESTIVATE. ESTIVATE utilized multiple regression (MR) equation predict machine subsequently, on basis this, estimate excavation costs. However, with coefficient determination (R2) 0.88 mean absolute percentage error (MAPE) 20%, MR failed provide an adequately robust predictor time. Improvement ESTIVATE's predictive capacity was sought use feed-forward artificial neural network back-propagation training. With sum square 0.194 MAPE 7% (that is, 14% reduction equivalent equation) provides significant improvement ov...