KOPYA NG SALIN 🔗
WEBVTT
00:00:00.640 --> 00:00:09.199
Welcome to Eco Ask Why, a podcast that dives into industrial manufacturing topics and spotlights the heroes that keep America running.
00:00:09.359 --> 00:00:16.399
I'm your host, Chris Granger, and on this podcast, we do not cover the latest features and benefits on products that come to market.
00:00:16.640 --> 00:00:28.079
Instead, we focus on advice and insight from the top minds of industry because people and ideas will be how America remains number one in manufacturing in the world.
00:00:31.839 --> 00:00:33.359
Welcome to Eco Ask Why.
00:00:33.439 --> 00:00:34.799
I'm your host, Chris Granger.
00:00:34.880 --> 00:00:36.880
I look forward to spending some time with you today.
00:00:36.960 --> 00:00:46.320
And we're going to be having some fun on this episode, diving into a topic that is it's at the doorstep of anyone in industrial manufacturing.
00:00:46.399 --> 00:00:49.200
Uh and it's data-driven manufacturing.
00:00:49.280 --> 00:00:50.399
And what does that look like?
00:00:50.479 --> 00:00:56.000
And how can we move beyond AI hype and basic control and really make sense of this?
00:00:56.079 --> 00:00:59.679
And we're super excited for this here at Electrical Equipment Company.
00:00:59.759 --> 00:01:06.560
Again, we're we're coming into our 100th year of being in the business, and it's just something we're celebrating big time.
00:01:06.799 --> 00:01:08.319
Looking forward to that big celebration.
00:01:08.400 --> 00:01:14.480
It's gonna be happening later this year, but you'll be hearing more and more about that, hopefully on EcoSY as we talk about it.
00:01:14.640 --> 00:01:24.000
And uh something that that that recently we recognize uh within industrial transformation conversations have evolved around two things, okay.
00:01:24.400 --> 00:01:30.400
And this is not gonna be earth shattering, but this is important automation and now AI.
00:01:31.120 --> 00:01:34.319
But here's the reality, here's some things that we recognize to be true.
00:01:34.560 --> 00:01:39.280
Most plants out there, industrial manufacturers, don't need more algorithms, right?
00:01:39.519 --> 00:02:02.000
What we need is better data discipline, okay, because the true frontier of modern industrial operations isn't just smarter machines, it's to shift towards a fully data-driven manufacturing ecosystem where that operational data becomes a strategic asset and not something like this as an overthought, okay?
00:02:02.159 --> 00:02:03.280
Because AI is powerful.
00:02:03.439 --> 00:02:16.159
I mean, we we all can admit that AI is powerful, but without clean, contextualized data, it's just noise at scale, and that's not going to serve us at all, no matter where we're at in manufacturing.
00:02:16.319 --> 00:02:22.400
And the real shift we need to think about is from reactive control to operational intelligence.
00:02:22.719 --> 00:02:26.240
Because traditional automation systems were reactive by design.
00:02:26.319 --> 00:02:27.199
Let's just think about that.
00:02:27.280 --> 00:02:30.960
Like PLC logic executed pre-programmed rules.
00:02:31.199 --> 00:02:34.240
When a signal changes state, this is gonna happen, right?
00:02:34.319 --> 00:02:40.000
This alarm's gonna be triggered, uh, and and um alarms will go off when limits were crossed.
00:02:40.159 --> 00:02:51.039
And that system worked very well, but it really didn't learn, and that's the differentiator because it's not whether or not your plant's automated, most likely it is.
00:02:51.280 --> 00:02:54.159
It's whether your plant understands itself.
00:02:54.319 --> 00:03:10.639
And when manufacturers begin capturing granular operational data, like machine speeds and tor profiles or any fluctuations in voltage or or operational operator interventions, they move from reactive to proactive, right?
00:03:10.800 --> 00:03:16.800
So we're not just reacting to control, we're proactively being intelligent, and that's a shift that's gonna change everything.
00:03:17.039 --> 00:03:24.960
Because the old model, think about that, they really rely heavily on clipboards, on pens, and just tribal knowledge, all that stuff, right?
00:03:25.120 --> 00:03:36.800
And the new model captures time-stamped, contextualized data streams that allow you and your teams to identify the bottlenecks invisible to just the human eye.
00:03:36.960 --> 00:03:38.879
Okay, and and you can't optimize.
00:03:39.039 --> 00:03:47.280
Think about this, you really can't optimize what you don't measure, and you definitely can't simulate it if you can't capture it.
00:03:47.439 --> 00:03:50.800
So you need to be able to simulate accurate data.
00:03:50.960 --> 00:03:57.120
Okay, so data quality is so important, it's the foundational of digital twins and predictive systems out there.
00:03:57.439 --> 00:04:01.520
And there's a there's a really a growing fascination with this idea of digital twins.
00:04:01.680 --> 00:04:13.680
We spent some time on EcoAs Wild talking about this because you're virtually representing physical systems, and that allows you to simulate performance on what that's gonna look like before you make a real world change.
00:04:13.919 --> 00:04:23.839
But here's what's missed so often when we think about this that the digital twin is only as good as the fidelity of the input data.
00:04:24.079 --> 00:04:24.879
That's it.
00:04:25.120 --> 00:04:38.720
So if you don't know exactly like when a machine is stopped, or why it's stopped, or under which low conditions forced it to stop, or what upstream or downstream events influenced it, then you don't have a digital twin, right?
00:04:38.800 --> 00:04:42.399
You have a digital guess, and that's not gonna serve you well.
00:04:42.560 --> 00:04:50.879
And AI agents require structured, high-resolution, real-time data to build usable relationships between these variables.
00:04:51.040 --> 00:04:55.839
And without that foundation, you really can't optimize, right?
00:04:55.920 -->
Load full transcript
00:04:58.800
And things are gonna collapse under ambiguity.
00:04:59.040 --> 00:05:03.839
So data-driven manufacturing starts really at the component level.
00:05:04.160 --> 00:05:06.079
This we're gonna talk about just for a little bit.
00:05:06.240 --> 00:05:20.160
The components, smart components are no longer passive devices, and you have devices out there like the E300 or C445, these are smart motor overload relays, and that's a fundamental shift in data architecture and how this works.
00:05:20.319 --> 00:05:22.959
And these are not just productive devices anymore, right?
00:05:23.199 --> 00:05:24.160
These are data hubs.
00:05:24.240 --> 00:05:26.720
I mean, this is really unreal the type of data you can get.
00:05:26.879 --> 00:05:41.519
So instead of just tripping or during a fall condition, which they're gonna do, they're continuously sampling and reporting back on voltage profiles, temperature trends, vibration, average peak current, current imbalance, you got torque estimations, you got energy consumption.
00:05:41.600 --> 00:05:43.040
The list goes on and on.
00:05:43.120 --> 00:05:49.279
And that transformation is gonna make it possible to go from reactive to predictive maintenance.
00:05:49.360 --> 00:05:59.519
Okay, instead of waiting for a catastrophic failure, you're you're gonna be able to receive alerts when performance is sort of starting to drift from anything that's from the baseline.
00:05:59.759 --> 00:06:02.480
And motors can be serviced during scheduled downtime.
00:06:02.560 --> 00:06:05.839
I have a big lot of a big history in being able to do this.
00:06:06.000 --> 00:06:14.800
Uh, and let me tell you what, when you service motors on your downtime versus an emergency shutdown, it's so much cheaper, so much less stress for everyone.
00:06:15.040 --> 00:06:19.519
Damn, that downtime becomes planned, not chaotic.
00:06:19.680 --> 00:06:25.199
And that difference shows up really big time on your PL and your balance sheet at the end of the day.
00:06:25.439 --> 00:06:27.600
So let's talk about OEE for a second, okay?
00:06:27.680 --> 00:06:32.480
Because OEE in the past, it was like a lagging indicator, right?
00:06:32.639 --> 00:06:40.480
But it could be a predictive lever, and and it's usually thought about overall equipment effectiveness is like a performance metric.
00:06:40.639 --> 00:06:48.160
But when you're doing a data-driven ecosystem, this it changes, it shifts from historical scoreboard to a predictive lever.
00:06:48.560 --> 00:07:06.639
Because when you have hundreds of variables being analyzed and thousands of variables simultaneously, like conductor speed or filler speed or torque or operator type of interventions, optimization of opportunities start to come to the surface, right?
00:07:06.800 --> 00:07:10.879
And this is what so think about shifting the the this question.
00:07:11.040 --> 00:07:13.120
What was our OEE yesterday?
00:07:13.759 --> 00:07:19.519
The question could be what variables can we adjust virtually to increase OEE tomorrow, right?
00:07:19.759 --> 00:07:21.600
Without increasing any risk.
00:07:21.920 --> 00:07:32.399
And that's the power of simulation when you layer it on clean data, and it's how manufacturers find those really sweet spots without breaking any physical equipment.
00:07:32.720 --> 00:07:42.000
So you really want to move from guessing to root cause precision and data that doesn't just optimize output, it clarifies accountability.
00:07:42.160 --> 00:07:56.079
Uh we we've had instances at an electrical equipment company where we saw a railroad manufacturing facility, they had repeat motor failures, and that led to assumptions of electrical defects, and the costs were this extravagant costs.
00:07:56.240 --> 00:08:00.399
But we were able to put in some of these smart motor relays and told a different story.
00:08:00.639 --> 00:08:10.560
It showed how these little snapshots and load history revealed how the how the equipment was being operated and how it was being overfed, right?
00:08:10.720 --> 00:08:16.399
And that really that uh overfeeding of the equipment caused the issues, okay.
00:08:17.040 --> 00:08:19.600
The issue wasn't hardware, the issue was our behavior.
00:08:19.759 --> 00:08:21.839
But without the data, we wouldn't have known it, right?
00:08:21.920 --> 00:08:23.759
We just kept replacing equipment.
00:08:23.839 --> 00:08:29.680
But with the data, we could address the root cause, and that's the difference between guessing and knowing.
00:08:29.839 --> 00:08:34.159
And the human advantage is is is data, right?
00:08:34.399 --> 00:08:36.799
Uh in the data-driven culture we live in.
00:08:36.960 --> 00:08:43.919
And the greatest, like if you start thinking about a misconception out there about AI and automation, the big misconception is that it's going to replace people.
00:08:44.080 --> 00:08:46.240
Like, no, bro, it's not going to replace people.
00:08:46.480 --> 00:08:48.080
They elevate people, right?
00:08:48.240 --> 00:09:10.799
Because when you have automated systems that are that are handling repetitive monitoring and data storing, engineers and technicians are freed up at that point to focus on strategic optimization or cross-functional system thinking or creative problem solving for things that are just popping up, you know, that that's newly risen to the surface or continually improving, right?
00:09:10.879 --> 00:09:12.159
That's what it's all about.
00:09:12.799 --> 00:09:14.480
Talented people, here it is.
00:09:14.799 --> 00:09:21.120
Talented people don't want to fight daily fires, they want to solve meaningful problems.
00:09:21.360 --> 00:09:36.080
And data-driven environments create space to do that, and they help build, uh, bridge these generational transitions because you have younger technicians and you have uh these guys are you know they grew up on smartphones and laptops and all that, right?
00:09:36.159 --> 00:09:44.320
Uh and dashboards, and now they're able to come
together and learn so much about the systems that they're integrating with and that they're working with.
00:09:44.480 --> 00:09:47.759
And this is not about replacing experience.
00:09:47.919 --> 00:09:49.840
We're about we need to amplify it.
00:09:50.080 --> 00:09:50.799
Amplify it.
00:09:50.879 --> 00:09:52.320
That's really what it's all about.
00:09:52.559 --> 00:09:56.799
And becoming data-driven is not like just something you just go buy some software.
00:09:56.960 --> 00:10:00.000
Like it's it starts with culture, it's a cultural commitment.
00:10:00.159 --> 00:10:03.919
It requires discipline, really, it's a discipline and data collection.
00:10:04.000 --> 00:10:07.519
Because if we're if we're gonna get good out, we've got to put good in.
00:10:07.759 --> 00:10:15.440
But it also means we need to make investment because you need to have sensors that can can handle and provide you the data that you need to make the right decisions.
00:10:15.679 --> 00:10:18.720
You need clean architecture between components and analytics, right?
00:10:18.799 --> 00:10:22.559
You got to have that clean architecture to be able to actually uh work with the data.
00:10:22.720 --> 00:10:25.120
You gotta have a leadership commitment, right?
00:10:25.279 --> 00:10:30.480
And you have to be willing to confront uncomfortable truths when the metrics show you that, right?
00:10:30.559 --> 00:10:32.559
You can't just hide from it and then run from it.
00:10:32.720 --> 00:10:47.759
And the plants that thrive in the next decade are not the ones that just gonna have AI, they'll have data integrity coupled with it, they'll have systems that learn, and they'll have teams that empower to act on insight instead of instinct.
00:10:48.000 --> 00:10:53.919
Now that instinct is bad, but instinct, when you couple it with insight, that's a powerful combination.
00:10:54.320 --> 00:11:03.120
And the future of manufacturing isn't just about smarter machines alone, it's about the overall smarter ecosystem.
00:11:03.360 --> 00:11:07.840
When raw operational data becomes strategic intelligence, right?
00:11:08.000 --> 00:11:25.600
That's a big deal because they because you'll, as the manufacturer, become more predictive, more optimized, you'll be reducing any type of waste, you'll have more engaged teams, and you'll create, and everybody's gonna love this, a substantial competitive advantage.
00:11:25.840 --> 00:11:27.279
So think about that.
00:11:27.759 --> 00:11:31.840
AI, when used correctly as a tool, changes everything.
00:11:32.080 --> 00:11:36.080
But data, clean, accurate data is the fuel.
00:11:36.320 --> 00:11:37.440
Culture's the engine.
00:11:37.600 --> 00:11:44.639
All right, so now manufacturers who line and all three of these are going to define the next era of industrial performance.
00:11:44.799 --> 00:11:48.320
And we're here to help you, we're here to serve it to serve you to walk along with you.
00:11:48.399 --> 00:12:02.720
If you need help with this, if you'd like to talk about it, if you'd like to get one of our experts to come to your manufacturing facility and talk directly, or maybe you want to come to one of our labs at Electrical Equipment Company, which we would love to have you come do that with us, reach out.
00:12:02.799 --> 00:12:05.360
We will have links in the show notes for you to connect with us.
00:12:05.440 --> 00:12:12.320
Uh, if this conversation, this just insights is if you found helpful and you want to share with others, we would be extremely grateful for that.
00:12:12.480 --> 00:12:15.039
Again, electrical equipment company were 100 years.
00:12:15.200 --> 00:12:22.080
We were just big, super excited for this night uh uh 2026, just think about 1926.
00:12:23.120 --> 00:12:35.039
I don't even know if this was on the radar uh for those guys that put that founded the company that we would still be here 100 years later, but here we are, stronger than ever, out here serving and growing, and we want to walk with you.
00:12:35.120 --> 00:12:37.519
So reach out to us at ecoonline.com.
00:12:37.600 --> 00:12:40.480
Uh again, share this podcast out and give us a direct review.
00:12:40.559 --> 00:12:42.080
Uh, look forward to seeing you next time.
00:12:42.159 --> 00:12:45.120
And remember, just keep asking why.
00:12:45.759 --> 00:12:48.320
Thank you for listening to Eco Ask Why.
00:12:48.399 --> 00:12:52.000
This show is supported ad-free by Electrical Equipment Company.
00:12:52.240 --> 00:12:58.960
Eco is redefining the expectations of an electrical distributor by placing people and ideas before product.
00:12:59.200 --> 00:13:02.159
Please subscribe and share with your colleagues and friends.
00:13:02.399 --> 00:13:06.639
Also leave comments, feedback, and any new topics that you would like to hear.
00:13:06.879 --> 00:13:12.960
To learn more or to share your insights, visit ecosy.com e co.
00:13:13.759 --> 00:13:17.440
A S A S W H Y dot com.