• Today, the effectiveness of real-time adjustments to drilling parameters may be hindered by uncertain surface and downhole measurements and the inability of humans to aggregate multiple streams of data in real-time. A recently introduced drilling optimization system addresses these issues by incorporating a Bayesian network into operators’ drilling rig data aggregation systems. This Bayesian network-enhanced decision-support system updates a probabilistic model in real time to track variations in drilling conditions. It identifies drilling dysfunctions by tracking the movement characteristics of various sensor data in relation to model-predicted values and aggregates this information to produce a holistic drilling optimization index. This novel “cone drilling” system combines Bayesian network-based dysfunctions identification with MSE tracking to create a single normalized quantity upon which drillers can make decisions to adjust drilling parameters.