A prediction model for the energy consumption of a belt conveyor system based on neural network

Energy consumption is the key indicator of speed control technology for improving energy efficiency of belt conveyor systems. This paper presents the design and verification of a short-term mathematical model intended for the prediction of energy consumption of a belt conveyor system using neural network method. The obtained model corresponds with real operational conditions. It can take advantage of operation parameters obtained according to the real experimental measurement. The concept of the experimental rig at Wuhan University of Technology of China is designed so that it represents a 3.5 m long belt conveyor system on which operation parameters acquisition experiments can be conducted. The performed experiments show a quick prediction with acceptable final results for real data with a short-term prediction horizon equal to 60 min and with a mean error of 4.8%. The obtained model is useful for analyzing the optimum speed of belt under real operational conditions and for optimizing operating procedures of belt conveyor systems.