22nd EANN 2021, 25 - 27 June 2021, Greece

Drilling Operations Classiļ¬cation Utilizing Data Fusion and Machine Learning Techniques

Marzieh Zare, Jussi-Pekka Lehtinen, Hesam Jafarian, Ari Visa, Liisa Aha

Abstract:

  Varieties of impediments expose the Mining industry to unexpected equipment failures, high commodity price damages, and various environmental difficulties and safety challenges. Therefore, we are looking for an appropriate approach to mitigate the cost of the sudden fault of Mining operations by increasing the automation level of monitoring and operating systems. To attain this goal, we utilize Machine Learning models and data fusion techniques on measured data values. As a result, we are capable of classifying the five diverse mining operations. The outcome of the method presented in this paper assists in the early fault detection of mining operations. This approach can support fault detection and prevention procedures. Besides, it leads to acceleration and enhancement of the maintenance and repair operations by simplifying the required query time.  

*** Title, author list and abstract as seen in the Camera-Ready version of the paper that was provided to Conference Committee. Small changes that may have occurred during processing by Springer may not appear in this window.