April 15, 2024

Computer vision and edge computing can shape the future of oil and gas

Currently, within information technology (IT), a major trend revolves around the empowerment of artificial intelligence (AI) and the Internet of Things (IoT) through edge computing, which accelerates Time to value for digital transformation initiatives. Santhosh Rao, senior research director at Gartner, notes that currently, approximately 10% of data generated by enterprises is created and processed outside of a traditional centralized data center or the cloud. Looking ahead, Gartner anticipates this figure will increase to 75% by 2025.

Expanding on this, edge computing is propelling computer vision into a new era, catalyzing the development of smart devices, intelligent systems, and immersive experiences. The inherent benefits of edge computing, including accelerated processing, increased security, and real-time information, have positioned it as a critical tool in various computer vision applications.

The last 12 months have seen a notable increase in interest in critical applications for computer vision at the edge, indicating a growing demand for failures.tolerant-Solutions based on. Cameras’ abilities to perceive things like thermal and infrared images (beyond the capabilities of the human eye) make them indispensable for identifying inconsistencies or vulnerabilities in various industrial processes, ultimately helping to improve workflow efficiency. and operational excellence.

This article delves into the key applications of computer vision in edge devices within the oil and gas industry, presenting distinctive opportunities to seamlessly integrate edge computing and computer vision.

Improving health, safety and environment (HSE)
Particularly in the oil and gas sector, the synergy between edge computing and computer vision is proving critical in addressing HSE concerns. Vision systems can now discern issues traditionally assessed by human personnel, including perimeter security concerns. This extends to monitoring flares and processes to detect hazardous conditions such as leaks or alterations in the chemical composition of the flares through temperature and color analysis. This plays a critical role in fire prevention and detection and facilitates emergency responses to catastrophic events such as explosions. Burn monitoring helps operators achieve smokeless burning, thereby improving their carbon footprint and minimizing overall environmental impact.

Additionally, cameras can be installed in real time to monitor the use of personal protective equipment, ensuring worker safety in hazardous environments. These AI-enhanced systems can even identify injuries and quickly alert response teams and authorities, ultimately improving overall safety standards in the industry.

Operations and reliability
Vision systems can also benefit the oil and gas sector by improving operational and reliability metrics. For example, a terminal can use vision systems to observe traffic flow and quickly identify if certain pumps, vehicles, lanes or operators are creating bottlenecks or slowing down compared to how they operated in the past. Engineers often have difficulty identifying why some assets perform better than others when all equipment appears to be the same. Vision systems can help identify and quantify the human element by observing the behaviors of high-performing operators and allowing those best practices to be taught to the rest of the team.

The best reliability engineers know that correlating data is key to identifying root causes and failure modes. Although many reliability departments include thermal and visible light imaging, these are snapshots in time and may not identify key events that have affected equipment. The inclusion of vision systems can bolster reliability by identifying these key events, correlating them with other reliability data, and quantifying the effect on reliability metrics. Vision systems offer the incredible ability to identify things you never knew before affected your operations.

Put computer vision-based insights into practice with Edge Computing
Today, there are three options to help incorporate these innovative, highly dynamic systems into operations to start gaining valuable, actionable operational intelligence.

Intelligent vision systems with integrated AI models. This involves using smart camera systems and accompanying vendor software to train the camera to detect a specific target scenario. While out-of-the-box functionality is highly beneficial for rapid deployment for individual sites or targets, several challenges must be considered. Some of those detrimental factors include high cost and supplier lock-in. However, the most notable problem with this approach is the limited scalability of the trained model, meaning that the model must be trained on one camera before manually moving to the other cameras so that they can learn from each other.

Standard cameras with cloud-based AI model. This is where the raw video is streamed to the cloud and the models are then trained on the cloud to detect predetermined targets. This comes with cost and data quality challenges and cloud egress fees, and can be difficult to integrate meaningfully into workflows. However, the advantage is that it provides good scalability, many open vendor tool options to improve serviceability, and a wide variety of training targets to help improve the flexibility of the technology.

Standard cameras with Edge AI model. This presents an opportunity to have the best of both worlds. One of the key advantages is having a variety of vendors to choose from (i.e. no vendor or software lock-in). You own your data and infrastructure, with a wide variety of targets to train for, highly scalable models, rapid deployment for individual sites and targets, and local integration into workflows. Instead, the biggest challenge is getting multiple departments to collaborate around a single edge computing platform (e.g., operations, IT, and procurement).

However, perhaps most important when comparing vision system architecture models is the integration of knowledge into workflows and actions. Owners/operators within the oil and gas industry can only achieve demonstrable gains in their digital transformation initiatives when they can react to what the vision system identifies. Using cutting-edge computing platforms, owner/operators can quickly and efficiently integrate into alarm systems, supervisory control and data acquisition systems, and enterprise resource planning systems; activate work orders; and connect data historians among other critical applications.

This is the key to getting value from a computer vision system. If you can’t quickly act on what your vision system detected, then there is little value in having a vision system.

Conclusion
In the oil and gas industry, transformative changes are occurring, driven by computer vision systems. However, adopting edge-native implementations is imperative to fully realize the potential of this technology. The speed, security and real-time information provided by cutting-edge computing position it as an indispensable tool for applications in this sector.

Fundamentally, vision systems alone do not instigate change; rather, they provide the insights needed to drive informed action. Achieving true change requires seamless integration of this knowledge into real-time workflows at the local level. As technology advances, continued innovations in edge computing and computer vision promise a future characterized by more secure, efficient, and intelligent systems and devices. This trajectory will transform everyday life both now and for years to come.

Leave a Reply

Your email address will not be published. Required fields are marked *