An Eye Tracking Based Framework for Safety Improvement of Offshore Operations

Abstract

Offshore drilling operations consist of complex and high-risk processes. Lack of situational awareness in drilling operations has become an important human factor issue that causes safety accidents. Prolonged work shifts and fatigue are some of the crucial issues that impact performance. Eye tracking technology can be used to distinguish the degree of awareness or alertness of participants that might be related to fatigue or onsite distractions. Oculomotor activity can be used to obtain visual cues that can quantify the drilling operators' situational awareness that might enable us to develop warning alarms to alert the driller. Such systems can help reduce accidents and save non-productive time. In this paper, eye movement char-acteristics were investigated to differentiate the situational awareness between a representa-tive expert and a group of novices using a scenario-based Virtual Reality Drilling Simulator. Significant visual oculomotor activity differences were identified between the expert and the novices that indicate an eye-tracking based system can detect the distraction and alert-ness exhibited by the workers. Results show promise on developing a framework which implements a real-time eye tracking technology in various drilling operations at drilling rigs and Real Time Operation Centers to improve process safety.

Keywords: Eye tracking; gaze; individual differences; offshore operations; saccades; safety; situational awareness.

Figure 1.

Offshore incidents in the Gulf of Mexico; Major = More than 3 days away from work or more than 3 days of restricted work or job transfer (collectively referred to as DART); Minor = 1-3 DART; and Other = Injuries that resulted in less than one DART (or those that required evacuation to offshore or to another offshore facility for medical treatment but did not result in any DART). (8)

Figure 2.

Eye tracking during drilling simulation at the Virtual Reality Drilling Simulator facility at the University of Oklahoma. Visual scan path data overlaid onto an operator’s view of sight: The center of the circles indicate the eye fixation location, the numbers in the circles indicate the time order of the eye fixations, the size of the circles indicate the eye fixation durations, and the linear lines indicate the fast saccades among the eye fixations. Visual search behaviors can be investigated using visual scan paths.

Figure 3.

(3a) The alarms received on a drilling rig in a week. The drillers can be inundated with this much information (After Goetz, 23); and (3b) A case study showing the parameters during LOWC and fire in South Timbalier area-2013 (After BSEE, 7)

Figure 4.

Eye tracking data at real-time operation center (RTOC).

Figure 5.

Virtual Reality Drilling Simulator (VRDS) at the University of Oklahoma.

Figure 6.

Area of Interests on the dynamically displayed well logging data (after NorskOlje&Gass (41)).

Figure 7.

Ocular data distribution of the expert during the full duration of the simulation 7(a) and during 2:00 to 2:50 second interval 7(b).

Figure 8.

Ocular data distribution of the novice during the full duration of the simulation 8(a) and during 2:00 to 2:50 second interval 8(b).

Figure 9.

Percent mean eye fixation duration 9(a) and count for the novice and the expert 9(b).

Figure 10a.

Mean fixation duration on all three AOIs by Novices, with expert’s values imposed in red.

Figure 10b.

Mean fixation counts on all three AOIs by Novices, with expert’s values imposed in red.

Figure 11.

Average change in pupil diameter (millimeter) of novice and expert while monitoring the real-time data during scenario execution.