[Smart Metals Podcast #14] Ensuring Data Quality in Metals Manufacturing: Techniques and Challenges

In this episode, Denis and I dive into something that’s not always in daily awareness, but it’s there—and it’s costing people time and trust: data quality.

You're not alone if this sounds familiar. Machines are running, numbers are coming in, and then someone says, “That doesn’t look right.” Suddenly, no one trusts the data, and you're back to guessing.

We talk through:

• What SCADA is really doing behind the scenes—and why that matters
• How bad data ends up in your ERP or MES without warning
• What to look for when working with time-series data
• Why manual checks don’t hold up once you grow
• How tools like Soda and Great Expectations can help

Listen here:

🎧 LISTEN NOW ➡️

If you’re in sheet metal and thinking about scaling, connecting machines, or just making better decisions with your data—this one’s worth a listen.

Thanks for being here,
Luke

Topics:
00:00 – 🎙️ Welcome to the Smart Metals Podcast
00:44 – 🔔 Big Announcement: Refocusing Business Activities
01:12 – 🔍 Understanding SCADA and Data Quality Challenges
04:37 – 🧪 Importance of Data Quality in Manufacturing
07:22 – ⚠️ Real-World Data Quality Issues and Consequences
11:04 – ✔️ Steps to Ensure High Data Quality
27:00 – 🛠️ Open Source Solutions for Data Quality Testing

Notable Quotes:
📢 "SCADA is the second layer of the automation pyramid—supervisory control and data acquisition. It collects data from PLCs and individual machines. The challenge is getting this high-frequency, millisecond-level time series data to the cloud. Data quality is one of the key problems in this area." – Denis Gontcharov
📢 "The reason we don’t have clean data is paradoxical—it’s assumed to be easy. People think if you move data from point A to point B, it should be correct. But that’s where everyone underestimates the problem." – Denis Gontcharov
📢 "Bad data completely erodes trust. One incorrect value and suddenly people stop using your dashboard. The whole data effort loses credibility." – Denis Gontcharov
📢 "Where should you check for data quality? A great place is in your pipeline—right after transformations. That’s where you catch issues before they hit your clean database." – Denis Gontcharov
📢 "Just like you don’t take raw ore and turn it directly into gold jewelry, raw industrial data needs to be processed, validated, and shaped before it holds value." – Luke van Enkhuizen

Relevant Links:
🔗 Follow the show: https://smartmetals.transistor.fm/
🔗 About Denis Gontcharov: https://gontcharov.eu/
🔗 About Luke van Enkhuizen: https://vanenkhuizen.com/

Sharing is Caring!
If you liked this episode, please consider sharing it with friends or colleagues who might find it useful. Thank you!

Would You Like to Help?
Did this show give you new ideas for your business? Then rate the show on iTunes or Spotify! ⭐⭐⭐⭐⭐
This helps others find the podcast and allows us to bring more industry experts to the show.