An offshore drilling rig has an extremely harsh working environment, which involves people from a wide variety of professions and cultures. Therefore, any solutions that aim to mitigate risks there must engage all sectors and stockholders, be based on existing culture, and comply with current procedures on rigs. This is not an easy mission, but neither is it impossible.
Monitoring systems powered by computer vision have become increasingly prevalent in the oil and gas industry, with companies using these technologies mostly to enhance their security. However, some proofs of concept have been conducted for safety purposes as well. These systems use artificial intelligence (AI) algorithms to analyze data from various sensors and cameras, allowing them to detect potential hazards and alert workers in real time. Such devices are equipped with cameras and sensors that can detect gas leaks, temperature changes, and other hazards, but they are also creating new challenges for safety crew.
While AI-based monitoring systems have proven effective at keeping workers safe, they have also introduced new challenges for health, safety, and environment (HSE) teams. Safety officers now must learn new technologies in addition to their existing duties. This can create additional workloads and stress for these people because they must balance their existing duties with the demands of learning and using new tools.
As such, it is important for organizations to consider carefully the benefits and drawbacks of these technologies and ensure that they are being used in the most effective and efficient manner possible.
This project aimed to identify and report mostly occupational risks on one of Petronas’ contractor drilling rigs on one of its platforms and save reporting and evaluation time by creating AI-generated dashboards benefitting different teams involved in drilling operations.
This rig is located in Southeast Asia, and approximately 70 staff work there at the same time. The rig is equipped with one fixed and eleven pan/tilt/zoom cameras. The cameras cover various areas on the rig, including fingerboard, casing board, below drill floor, drill floor, wireline, derrick levels, flowline, drawworks, crown, and shale shakers.
The AI-based platform was set up on the rig and connected to the cameras to receive the streams. The AI engines ran the desired models on each stream and made required concepts that are necessary to articulate occupational risks.
The risks were defined in terms of basic risk factor (BRF) in several scenarios in close collaboration with the health and safety team and offshore installation manager and other contractor team members with their considerations according to the processes and operations handled in each area.
The method used here was to analyze real-time visual data captured by closed-circuit television cameras using computer vision. Furthermore, a scenario-based AI engine was developed that applied HSE logic based on BRF and rules to generate final data. This approach helped to create a report system that was familiar and practical to end users.