Deep learning-based prediction of piled-up status and payload distribution of bulk material

Abstract

The piled-up status of bulk material in a haul truck body determines the load balance, hence affects the mining operations’ efficiency. Prediction of Piled-up Status and Payload Distribution (PSPD) of bulk material contributes to providing optimal dumping positions to improve the vehicle’s stress state and service life. This work introduces a novel deep learning-based PSPD prediction method from images. A two-stage prediction-regression CNN model is designed to automatically extract image features to obtain the PSPD of the current state. The PSPD prediction is accomplished via a backward-propagation neural network (BPNN). Scaled model experiments are performed using robots for validating the method. Experiments show the trained model accurate and reliable in prediction and computationally efficient. The probability density of the prediction error is subject to the Cauchy distribution with x0 of −0.00043 and γ of 0.01986. The maximum prediction error is 0.19kg (about 3.17% of total weight).