Paper Title
Machine Learning Appliance for Drilling Operations Events Visualization and Optimization: A Focus on Energy Technology

Abstract
With the increase in worldenergydemand, thereis an increasingdemandforhydrocarbons, so thattheexplorationofoilfieldsis still ofgreatimportanceworldwide. Itis possible tomaketheseactivities more economically viable by improving the efficiency ofthedrillingprocess. Computational tools, as the one proposed by UFES through feature XDrill advanced, enables automated and dynamic pre-operational tests with less human intervention, determining parameters that enable an operating efficiency gain in drilling. In addition, it is possible to analyze keytoolmobilizationperformancefactors, which do not mean rock penetrationoptimization, but specifically tooling operations. Withspecificbenchmarks, itis possible toanalyzewhetheroperatorsaredevelopingtheiractivities in the industry metric within a standard time, and thus suggestimprovementsforframingtheaverage time tothe end activity. In the end, ensuring these, there are less exposure to hazardous environments, astheuptimehasdecreased, also helping in possible decreases in terms of incidents and accidents do to less exposure. Sequentially, itis possible totendtoimplement an automatedplatformwithlittledrillerintervention so thatthebaseparameters (RPM, WOB, FLOW) canbeautomaticallyset. Processdigitization and automationisvery evident in themarket, supportingthistechnologicaladvance. This wholeprocessisdirected, couplingtheparticularsof exploration in the unconventional fields, including pre-salt and shale related activities. The use of artificial intelligence and pattern visualization / recognition are actively present, showing a huge gain in terms of relationshipbetween Energy, environment and sustainability, as a powerful energy technology computation tool. Keywords - Energy; Tool; Technology; Pre-Salt; Shale.