Abstract: K. Anvari, A. Mousavi, A. R. Sayadi, E. Sellers, E. F. Salmi (2022)

The collection of sensor-based data is dramatically increased in the mining industry. One of the widely used applications of the collected data is to identify rock domains and to estimate rock mass properties. Rock domaining and classification are usually done by engineers and geologists based on manual downhole logging and using engineering judgments and expert interpretation. However, such human-centered processes are time-consuming, costly, and often have low precision as they are subjective to personal interpretation. On the other hand, with the emerging of real-time recording technologies on drilling equipment through sensors, it is necessary to distinguish the rock boundaries in real time so that the recorded data can be used to optimize decisions. The main objective of this study is, therefore, to develop approaches to automatically determine rock domains in mining operations by using a hybrid recurrence quantification analysis (RQA), quadrant scan (QS), and machine learning (ML) methods to both recognize the boundaries of rock domains and to classify the rock masses based on their physicochemical features. The proposed method was applied on a multivariate geochemical assay dataset of an iron ore mine, and the results were evaluated against the downhole logging recorded by geologists and the wavelet transform method as a comparative analysis. Results show that by using RQA, QS, and ML techniques, it is reasonably possible to quickly determine the rock domains and to characterize them according to their physicochemical characteristics.

Please note: The abstracts of the bibliography database may underly other copyrights.

Ihr Browser versucht gerade eine Seite aus dem sogenannten Internet auszudrucken. Das Internet ist ein weltweites Netzwerk von Computern, das den Menschen ganz neue Möglichkeiten der Kommunikation bietet.

Da Politiker im Regelfall von neuen Dingen nichts verstehen, halten wir es für notwendig, sie davor zu schützen. Dies ist im beidseitigen Interesse, da unnötige Angstzustände bei Ihnen verhindert werden, ebenso wie es uns vor profilierungs- und machtsüchtigen Politikern schützt.

Sollten Sie der Meinung sein, dass Sie diese Internetseite dennoch sehen sollten, so können Sie jederzeit durch normalen Gebrauch eines Internetbrowsers darauf zugreifen. Dazu sind aber minimale Computerkenntnisse erforderlich. Sollten Sie diese nicht haben, vergessen Sie einfach dieses Internet und lassen uns in Ruhe.

Die Umgehung dieser Ausdrucksperre ist nach §95a UrhG verboten.

Mehr Informationen unter www.politiker-stopp.de.

Automatic detection of rock boundaries using a hybrid recurrence quantification analysis and machine learning techniques