Resumen
The Inertial Measurement Unit (IMU) is widely used in the monitoring of mining assets. A good example is the Polish underground copper ore mines of KGHM, where research work with the use of the IMU has been carried out for several years. The potential of inertial sensors was ensured by the development of advanced analytics using machine learning methods to support the maintenance management of an extensive machine park and machine manufacturer in adapting various construction elements to mining conditions. The key algorithms developed in the field of inertial data concern: identification of cycles and components of the haulage process operations, identification of dynamic overloads, technical diagnostics of rotating elements, assessment of road conditions (bumps, slopes, damages), assessment of the technical condition of the pavement, assessment of the operator?s driving style, and finally the machine location in the mining excavation. One of the key operational contexts, necessary in the development of analytics for underground mining vehicles, is the identification of the turning moment of the machine at the intersection together with the determination of the driving direction and the turn angle. In the case of a mine with a room-and-pillar system, where the excavation system has the Manhattan structure, it is possible to use many simplifications to correctly estimate the machine motion path. The identification of the spatial context and the turning maneuver is of key importance both in the development of the machine location system, but also in multi-dimensional analyzes, including the analysis of dynamic overloads or the assessment of the operator?s driving style and work safety. The article presents a comparison of several mathematical models used for the machine turn detection problem, which were trained and tested on the real-life industrial data recorded using IMU during a single working shift of the self-propelled machine.