An Algorithm to Process Big Data of Remote Technical Condition Assessment System for Mining Machines

Abstract

In the context of the development and integration of highly automated vehicles into the transport systems of mining enterprises, it is essential to maintain up-to-date information on the technical condition of mining equipment. An analytical model has been developed to predict the condition of robotic mining systems by processing data received from the equipment in real time. To enable remote monitoring, an algorithm has been proposed that performs automated multi-parameter diagnostics by detecting patterns in the behavior of critical operational parameters. This algorithm estimates the remaining service life and identifies failures or non-operational states in specific machine components. Additionally, the Hooke and Jeeves pattern search method has been applied to determine the number of critical parameters of mining machines. Experimental research was conducted to evaluate the operating parameters of the power unit. A technical solution has also been introduced—an automated system for integrating vehicles with the transport infrastructure—which enhances the functional capabilities of mining equipment. The implementation of this integrated approach to remote diagnostics allows for forecasting changes in equipment condition during operation and contributes to improve safety and efficiency of transport processes.