How To Get Information Technology And Operational Technology Staff To Work In Harmony

Oil and gas are moving many applications to the edgeFOGHORN

Technological shifts in the industry are needed to continue to meet demand and deliver profits. Traditionally information technology (IT) and operational technology (OT) staff have worked on opposite sides, siloed from each other – not overlapping on projects or deployments.

However, in the world of industrial IoT (IIoT) that approach has been flipped, demanding that these departments be entirely in sync and aligned. With Gartner’s prediction of 60% of IIoT analytics coming from IIoT platforms coupled with edge computing, OT/IT convergence is necessary to prepare for this influx of IIoT analytics for continued, if not improved, performance and output from refineries and drilling operations, along with individual machines involved in those operations.

One concern for aligning teams on IIoT investments and deployments is the differences in languages used. To get these two teams on the same page, IIoT deployments must incorporate a tool that eases translation, so OT teams are easily able to express, in code, their experience and tribal knowledge of machine behavior to drive meaningful analytics and insights on machine performance that the IT teams can use in machine learning models.

By connecting these teams, both win – IT has the specific knowledge integrated into data models that continually learn and adjust themselves for continued improved outcomes, and OT automates their workflows and has insights to better monitor for anomalies and optimize operations and maintenance for maximized outcomes. Moreover, those factories that have converged their OT/IT teams have proven successful results, such as reduced energy consumption, product quality improvements, asset health improvements and avoided unexpected downtime.

Taking needs to the edge

“The oil and gas industry, in general, does not favor connecting their assets to a cloud environment for fear of cybersecurity attacks, among other concerns,” Sastry Malladi, CTO of edge intelligence solution provider, FogHorn explained. “Because of this trend, oil and gas organizations have brought the computing needs to the edge within their existing constrained environments.

“However, the teams that operate and manage these devices are OT staff that don’t always have the knowledge needed for the edge environment. Because of the overlap between the technology needs and the environment requiring it, there is a natural need for a closer collaboration between OT and IT people in this sector.

“Another factor driving this collaboration is the fact the computing devices available at the edge are existing controllers, PLCs and drilling equipment that has embedded systems. Neither IT staff, not OT staff alone can get these systems to work with the advanced edge computing technology. They have to leverage both of their strengths to make this happen.”

Like every other initiative, learning curves are to be expected for people with new technologies and approaches. “We are constantly learning where the friction points are between these two teams and have been addressing this in terms of tools where the OT staff expresses their desired outcomes or behaviors, and our tools translate that into what IT staff can understand to deploy into these constrained devices,” Malladi added.

Speaking a different language

When it comes down to it, OT and IT teams talk a different language, and on top of that, they traditionally have been siloed from each other. For example, when an IT person talks in terms of machine learning models, inferencing AI, or the need for better data for training the models accurately, the OT staff may not fully appreciate that. OT staff speaks in terms of machine health, failure prediction, and condition monitoring. A person or tool must bridge this gap, so they can effectively collaborate.

FogHorn’s tools allow OT staff to express the available sensor streams easily and, in many cases, enable auto-discovery of those. Then those streams are automatically made available when authoring analytics or machine learning-based use case definition, without requiring back-n-forth communication with IT staff.

Meeting customer needs

“There are several examples where we have successfully deployed our solution to address customer needs,” Malladi added. “One example is real-time flare monitoring of a multitude of flare stacks in a gas refinery using a video sensor/camera with the largest oil and gas producer in the world.

“Our solution monitors this video for specific flare conditions, combining it with other sensor data and alerts field staff if either significant flaring or smoke is coming from the stack indicating problems up the processing chain. With edge computing, the video feed, previously manually monitored, is analyzed with deep learning programs in real-time to alert operational technicians of problems.

“The frame by frame flare processing combined with other information, such as a pressure valve and an acoustic sensor on the compressor, allows for further analysis of the root cause of the flaring that results in better business optimizations for the customer.

Benefits for industry

While this particular use case benefits oil and gas end-users in two ways: Alerting staff to problems before they’re potentially destructive and reducing the impact of compliance related fines for excessive toxic gas releases, customers are deploying our technology across many different use cases.

Additional use cases typically involve either predicting failure conditions in various scenarios, doing predictive maintenance, asset performance optimization, condition monitoring of equipment, reducing the operational failures and costs, improve and ensure product quality, improve asset health and avoid unexpected downtime.

 

[“source=forbes”]

, , , , , , , , , ,