Big Data Based Models of Operators Cognition and Situational Awareness during Process Operations

Process industries continue to suffer from accidents despite significant regulatory intervention since the mid-1980s and major developments in process control, monitoring and supervision technologies over the last four decades. Human error is widely agreed to be the major contributor to most accidents today. The traditional approach has been to look at human error as the initiating event of incidents, one that has a given likelihood of occurrence, similar to the way that a piece of hardware is expected to fail at some frequency. Just like equipment monitoring relies on detecting prognostic signatures of its impending failure, well in advance of the actual occurrence so as to trigger timely intervention, one can ask, is it possible to detect human error before it is committed?

Cognitive engineering is concerned with the mental processes of the human actor, such as perception, memory, reasoning, and motor response especially in the context of  his/her interactions with other elements of a system. In this talk, we will provide an overview of recent developments from cognitive engineering such as eye gaze tracking and pupilometry,  which offer real-time high velocity, high volume data on the cognitive performance of operators. We will demonstrate using results from recent experimental studies that these data can be used to build models of operators’ situation awareness.  Operator’s situation awareness (SA) levels can be monitored using these models, i.e., when their SA is low,  operators are highly likely to take incorrect control actions with the potential to cause incidents and accidents. We will also describe a number of other potential applications of these operator monitoring models and technologies.