A novel artificial intelligence automatic detection framework to increase reliability of PLT gas bubble sensing

Abstract Production logging tools (PLTs) and formation testing, even in while drilling (LWD) conditions during underbalanced drilling, are key technologies for assessing the productivity potential of a gas well therefore to maximize recovery. Gas bubble detection sensors components determining fluid phases reservoir accurately quantify recoverable reserves, optimize placement, geosteering qualify production ability well. We present here new nonlinear autoregressive - breakdown artificial intelligence (AI) framework PLT that categorize real-time whether which become unreliable or have broken down measurements. AI allow automatization this method is critical data quality control post-drilling PLT, but it essential when measurements performed LWD as assessment processing need occur real-time. This was validated on both training testing dataset, exhibited strong classification performance. enables accurate sensors.