Machine learning can reduce false alarms on rigs, well control incidents

Modern drilling rigs use electronic systems to alert crews to potentially hazardous or costly events such as kicks, losses or spills, but wide fluctuations in measured values generate many false alarms. This can lead to alarm fatigue in crews and, consequently, well control incidents, Sean Unrau, Product Line Manager at Pason Systems, said at the IADC HSE&T Conference in Houston. In this video from the event on 6 February, Mr Unrau discusses how machine learning can be used to significantly reduce false alarms and improve rig safety through early detection. He also highlights results from an analysis of 80,000 hours of data from rigs equipped with machine learning technology, in which all 33 kicks that occurred were detected before the gains outgrew 2.5 bbl and all 20 losses that occurred were detected before the loss outgrew 6.3 bbl. Further, the false alarm rates for kicks and losses were less than one every 5 hours and one every 10 hours, respectively.