Pipeline Integrity Management and Data Science Blog

Crack Fatigue Analysis as a Cloud Service

The more time we spend with our clients the more we learn they are reliant on spreadsheets. To this point, we’ve jokingly considered changing our mission from “Predict pipeline failures, save lives and protect the environment… with the assistance of Machine Learning” to “We eliminate legacy Microsoft Excel spreadsheets”. Of course, all joking aside, we want to enable integrity management teams to spend their time doing high-value engineering.

The latest Microsoft Excel sheet we have replaced is a customer’s version of a Crack Fatigue Analysis based on the modified Ln-Sec equation for cracks in pressurized pipelines. As we run across these types of legacy spreadsheets and look to incorporate them into our solutions, we generally assess the business value proposition based on the following three primary areas:

  • How much does it currently cost the client to perform this business function?
  • How much time and resources are being consumed by this activity?
  • How accurate are the results?

Once we know these things, we ask ourselves a simple question – Will data science and the cloud help do it faster, cheaper, with better results, and still provide a reasonable ROI?

Case study

A client of ours typically analyzes 40 crack runs per year and was outsourcing a portion of the analysis to a 3rd party at a substantial cost. For those they ran internally, an integrity engineer would import the crack ILI log and pressure data into Excel, set the parameters for the process, hit go, and put the computer on a desk for weeks at a time while it cranked away.

Below is a picture of the desktop computer cranking away on a crack run with 4,800 cases. At this point, it had been running for three weeks.

As a result of this, they decided to give us the same data and asked that we run it. We gave the file to our data science team, they kicked off the process, and three hours later it finished. In fact, our product manager reviewed the results with the client’s integrity team while the desktop computer was still running.

We’re close to moving this feature from preview to production. Once complete, it will show up in our Cognitive Integrity Management solution as another condition to run. On top of this all, the process is extremely simple. It will cost $1,500 per log, require someone to drag the ILI log and pressure data onto our Cognitive Integrity Management solution, and a few hours later the integrity engineer will be able to use our business intelligence to determine what cracks need to be reviewed.

We’d be happy to repeat this process for you. Shoot us a note and we’ll gladly start eliminating Excel spreadsheets for you too.