Skip to main content

Bridger Pipeline Uses PowerAI Solution to Predict and Detect Pipeline Leaks

To improve system sensitivity and speed of response to pipeline leaks, Bridger Pipeline chose to work on a paid proof-of-concept engagement with IBM.

Man looking out over factory

Pipelines are vital to moving hydrocarbons across vast geographic locations, and while doing so, reducing emissions related to hydrocarbon transportation via road and rail. Despite best intentions, however, pipeline leaks can sometimes occur.

Realizing this simple truth, Casper, Wyoming-based Bridger Pipeline LLC wanted to ensure it could rapidly and effectively shut off leaks before they could damage the local environment. Although the company was already transporting close to 100 percent of its oil to its various final destinations, it believed new technologies could help eliminate the remaining fractions-of-a-percent in losses.

As Tad True, Bridger Pipeline vice president, explains, “We’re a family-owned company with a lot of pride in what we do, so we take any kind of impact on the environment incredibly seriously. Besides the enormous clean-up cost, a pipeline that leaks is completely unacceptable to us from an environmental and reputational standpoint. One of our core mission statements is to protect our good name and integrity, and we’re constantly investing in new capabilities to eliminate leakage.”

False Positives

With approximately 3,500 miles of pipeline to manage, Bridger Pipeline was facing significant challenges detecting and resolving leaks in a timely manner. Moving 450,000 barrels through its pipeline network every day, it had established a monitoring system that uses smart meters and satellite-enabled surveillance systems that delivered massive volumes of real-time data into its control center 24-7.

“The experts in our control center must predict how turning on a pump or closing a valve will affect the flow of oil hundreds of miles away,” True says. “They rely on sensor data to support their experience and intuition, but our existing system was generating too many false alarms. One major risk in our industry is controller fatigue: People may start to ignore genuine alarms because they believe them to be a fault in the detection system.”

To improve system sensitivity and speed of response to pipeline leaks, Bridger Pipeline wanted to augment the existing capabilities of its control-center experts. In response to this, the company reviewed third-party solutions that might help increase leak detection. But due to its continuing growth and a constantly changing pipeline network, it found off-the-shelf solutions to be costly, inflexible and impractical.

“The existing systems require a team of people to study your network, then spend up to nine months on implementation,” True notes. “And every time you change your pipeline network, you have to bring those people back out to update the leak-detection system.”

Improved Visibility

This encouraged Bridger Pipeline to consider deploying an artificial intelligence (AI) solution that uses deep learning techniques to reduce false alarms and rapidly and efficiently detect even minor leaks. After speaking with several potential providers, it chose to work on a paid proof-of-concept engagement with IBM.

“What appealed to me about IBM’s approach was the number of questions the consultants asked,” True recalls. “They knew what their deep learning platform was capable of, and they wanted to understand our challenges and all the data we could provide.”

After these initial discussions, IBM built a test environment based on its IBM PowerAI Enterprise offering. A suite of AI software featuring open-source machine learning frameworks such as TensorFlow and Caffe, it’s optimized for the IBM Power Systems* platform. Based on the successful proof-of-concept exercise for PowerAI, Bridger Pipeline anticipated a dramatic reduction in the number of false alarms and a significant increase in leak-discovery sensitivity.

This prompted the company to give the go-ahead for a full production environment, confident that the solution was up to the task of accurately predicting and detecting leaks. True Oil and IBM decided to deploy the AI solution on an IBM Power Systems AC922 server with two IBM POWER9* processors (for a total of 44 processor cores) and four NVIDIA Tesla V100 graphic processing units (GPUs). The AC922 uses next-generation NVIDIA NVLink technology to provide up to 5.6x more bandwidth between CPUs and GPUs than would be possible with PCIe Gen3 technology used in x86-architecture servers.

The joint team is currently training the solution using historical data on flow rate, pressure, volume and other pipeline metrics throughout the network, and will initially run it on a 40-mile section of pipeline to benchmark its performance against Bridger Pipeline’s existing monitoring system.

The Ultimate Goal

Bridger Pipeline was already confident in the ability of its controllers to detect catastrophic failures and take mitigating actions almost instantaneously to prevent damage to the environment, but the new PowerAI-based solution augments those capabilities by providing visibility into smaller leaks that might otherwise go undetected.

“The IBM solution on PowerAI essentially gives our experts the ability to detect and resolve much smaller leaks, which is vital as we work towards our ultimate goal of zero loss from the network,” True says. “What we’ve achieved in just a short time is pretty remarkable. We believe we’re already competitive with the commercial systems we initially considered, and, unlike those solutions, ours requires no costly or time-consuming rework if something changes in the network. And thanks to the deep learning approach, we expect that the accuracy of the solution will continue to improve as the volume of data grows.”

With the PowerAI solution cutting down the total number of alarms, the risk of controller fatigue or overload also falls. Each alarm can then be analyzed faster and more comprehensively, and the actual leaks addressed sooner.

Pushing the Boundaries

In the coming years, Bridger Pipeline plans to build up its internal skills in AI and deep learning so that it can extend the solution to address applications such as predictive maintenance around pipe corrosion and the avoidance of inefficient turbulent flow in pipelines. The company also has plans to commercialize and offer its leak-detection solution to other oil and gas companies.

“We’re already seeing the benefits of the PowerAI solution in reducing false positives and enabling us to identify even the smallest of potentially harmful leaks,” concludes True. “As we strive to be the best stewards of the environment that we can, we’re proud to be working with IBM to push the boundaries of AI applications in our industry.”

IBM Systems Webinar Icon

View upcoming and on-demand (IBM Z, IBM i, AIX, Power Systems) webinars.
Register now →