Dynamic Prediction and Optimization of Energy Consumption in Mining Equipment Using Mobile Computing Platforms

Abstract

With the increasing energy consumption in the mining industry, the effective prediction and optimization of energy consumption in mining equipment have become pressing challenges. Traditional energy consumption prediction methods suffer from data processing delays and the fixed nature of monitoring devices, making them inadequate for meeting the real-time and flexible demands of modern mining operations. The advent of mobile computing platforms has introduced new possibilities for the dynamic prediction and optimization of energy consumption in mining equipment. In recent years, energy consumption prediction techniques based on mobile computing platforms have gained significant attention, enabling realtime data acquisition and analysis for a more precise understanding of energy consumption patterns and the implementation of efficient optimization strategies. However, existing studies predominantly focus on conventional models and methodologies, lacking effective mechanisms to capture spatiotemporal dynamics and optimize energy consumption accordingly. In this study, a spatiotemporal gated graph convolutional prediction model was proposed for the dynamic prediction of energy consumption in mining equipment based on a mobile computing platform. Additionally, an energy consumption optimization strategy was explored using the prediction results. This study provides a novel approach to energy consumption optimization in mining equipment, offering both theoretical significance and practical value.