In mid-July, Eugene, Oregon hosted the world’s Track and Field Finals. I’m not an athlete but I admire these competitors. They work their entire lives for the possibility of glory. The relay race is by far the best event. It’s not just one athlete doing their best. It’s four colleagues working in tandem, racing for the gold. Thrilling! But behind that competitive spirit is a lot of hard work. True champions know the journey is just as important as the 60 second sprint to glory!
I was on a customer champions call recently. I call it “champions” because those on the call were like-minded “athletes” looking to collaboratively solve the data quality issues they regularly encounter in their OSIsoft PI data. Looking to join champion status, they spoke to several common themes including:
- The primary motivation of improving PI data quality is the risk of missing something analytically, thus impacting performance, due to bad data
- The need to fix bad data before analysts use it in their models because bad data cause performance value models to fail.
- The understanding that PI, as a trusted system of record, is only valuable when you have 100% confidence in its data quality
- The methodology required to scale and maintain a fleet of quality data for millions of tags
- The conclusion that the ROI on fixing PI data quality is the ability to remain competitive and there’s real risk by doing nothing
They all admit they know some of their PI data is bad, but not to what extent. If they knew how bad, they could fix it. Many said they’ve been working on this data quality problem for decades. But now it’s putting their value-added initiatives—like analytics, APC, process optimization, predictive models, AI, etc.—at risk.
Whether you are the PI system administrator, the PI end user, the IT leader, or a data scientist, you need good data to deliver optimum business value to your organization. Luckily, APERIO can help. Like a good coach, APERIO can set you up for success. APERIO DataWise for PI can calculate data quality so that you can identify missing, bad, and stale PI data, and then, monitor, track, and instantly improve the integrity of your PI data over time. This machine learning technology measures data quality by ensuring its accuracy, consistency, completeness, validity, integrity, and timeliness. It can alert at the highest possible level of the asset framework with insight and recommended actions to resolve poor PI data issues.
Looking to start your journey? Download the APERIO DataWise for PI eBook to learn more.
Livia Wiley has over 25 years of experience focusing on strategic planning, industry growth, and process innovation. Her engineering background is underpinned by broad industry expertise and applications of industrial automation software, having worked for AVEVA, Schneider Electric, Honeywell, and Aspen Technology. Livia holds a B.Sc. in Chemical Engineering from Queen’s University and a M.Eng in Chemical Engineering from the University of Houston.