1 00:00:00,430 --> 00:00:03,230 Good morning, everyone, and thank you, Jake, for that introduction. 2 00:00:03,230 --> 00:00:05,230 So, yes, hi, I'm Dominique. 3 00:00:05,230 --> 00:00:07,070 Most people call me Dom. 4 00:00:07,870 --> 00:00:12,350 I am a technology consultant on our software and control team for Rockwell Automation. 5 00:00:12,510 --> 00:00:21,630 If you are unfamiliar with us at Rockwell Automation, we are the largest industrial automation and industry 4.0 company in the world. 6 00:00:22,430 --> 00:00:26,590 We are a global company however, I am local support here in Iowa. 7 00:00:27,070 --> 00:00:33,950 I live here in Des Moines, and I help support our Iowa and Minnesota regions for adopting and sharing about our technology here. 8 00:00:33,950 --> 00:00:38,750 I specifically focus on our information software, such as AI and things like that. 9 00:00:39,950 --> 00:00:40,230 Yeah. 10 00:00:40,350 --> 00:00:49,830 So my goal today is to be able to give some real life examples of how AI can be implemented on the factory floor today. 11 00:00:49,830 --> 00:00:53,470 And we'll run through some scenarios of that and some challenges. 12 00:00:53,470 --> 00:00:57,790 I also do have a live demo, a couple of some videos, a live demo. 13 00:00:57,870 --> 00:01:02,990 I hope the live demo works out well because that is our generative AI demo. 14 00:01:04,269 --> 00:01:04,670 So 15 00:01:05,190 --> 00:01:11,950 I'm going to start with some modern production challenges that we see today on the plant floor. 16 00:01:12,510 --> 00:01:16,270 The first one is a big one, workforce and skill shortages. 17 00:01:17,070 --> 00:01:23,070 So when I started at Rockwell Automation, I've been at the company for almost three years after I graduated from Iowa State. 18 00:01:23,630 --> 00:01:25,710 I actually had no idea what a PLC was. 19 00:01:25,789 --> 00:01:27,150 I didn't know what a controller was. 20 00:01:27,350 --> 00:01:29,550 Electrical engineering was my worst subject in school. 21 00:01:29,630 --> 00:01:30,990 I was a mechanical engineer. 22 00:01:31,390 --> 00:01:40,030 So I got in there and I have to learn how to code PLCs, how to code HMIs, all of those fun things, stepping into a completely new world. 23 00:01:40,509 --> 00:01:49,550 And if you know Rockwell or really any industrial automation how to code it, it looks very different from what a software engineer does today. 24 00:01:50,030 --> 00:02:03,950 So we're definitely seeing that with kind of a transition from the older workforce with a more EE electrical engineering focused focus to more of a software engineering, C, Python, that kind of thing. 25 00:02:04,510 --> 00:02:06,910 The other one is localization of critical manufacturing. 26 00:02:07,470 --> 00:02:14,870 So we're seeing that these global companies, they're really focusing on localizing their supply chain and localizing their plants. 27 00:02:14,870 --> 00:02:16,670 So we see some challenges with that as well. 28 00:02:16,910 --> 00:02:24,270 That 64% of manufacturing leaders are doing focuses on regionalizing their manufacturing processes. 29 00:02:25,070 --> 00:02:29,070 The next one is operational complexity and quality pressure. 30 00:02:30,510 --> 00:02:34,310 I have seen some crazy stuff in the field, some crazy complex stuff. 31 00:02:34,310 --> 00:02:37,150 I'm sure some of you guys have that on your plant floor today. 32 00:02:37,790 --> 00:02:41,630 The first time I saw a super crazy machine, I thought it was like Charlie and the Chocolate Factory. 33 00:02:41,950 --> 00:02:43,870 I was like, there's no way this is real. 34 00:02:43,870 --> 00:02:48,590 Like how does somebody code that and process that and make everything all of that work together? 35 00:02:49,470 --> 00:02:50,910 And that's just going to keep going. 36 00:02:51,070 --> 00:02:52,910 We're going to keep getting more complex. 37 00:02:53,470 --> 00:02:59,630 And so that is just, you know, something that a challenge that people are facing today. 38 00:03:00,470 --> 00:03:07,470 And one of the last ones, and when it comes to AI, I think this is one of the biggest ones, is fragmented and inaccessible data. 39 00:03:08,670 --> 00:03:16,750 So right now, I see kind of two different scenarios when I go and go do plant tours and see customers. 40 00:03:17,310 --> 00:03:22,990 The first one is that they are sending all of their data into one database and one data lake. 41 00:03:23,510 --> 00:03:25,230 And I say, okay, that's awesome. 42 00:03:25,710 --> 00:03:26,670 What are you doing with it? 43 00:03:27,390 --> 00:03:29,230 And they're like, we don't know. 44 00:03:29,950 --> 00:03:33,030 We were told we needed to send this data and have it sit somewhere. 45 00:03:33,030 --> 00:03:36,829 I was like, oh, do you have a data scientist team? 46 00:03:36,829 --> 00:03:39,790 Do you have anybody that's looking at that doing analytics? 47 00:03:39,790 --> 00:03:41,070 Nope, we don't have that. 48 00:03:41,590 --> 00:03:43,550 I'm like, okay, so that's one thing. 49 00:03:43,590 --> 00:03:46,670 The other thing I see is these data silos in a plant. 50 00:03:47,070 --> 00:03:54,750 So we have our different production areas, all of those, they have their data in their area, not really accessible to other areas of the plant. 51 00:03:55,390 --> 00:04:02,110 And when it comes to building an AI agent or just looking from an analytics side at how our plant 52 00:04:02,590 --> 00:04:10,910 is operating across the entire plant, that can be also really difficult when we have all of these data, all of this data in all of these different places. 53 00:04:11,230 --> 00:04:17,550 How do we combine that to make a full picture of our plant or be able to feed that into some kind of an AI model? 54 00:04:20,990 --> 00:04:27,310 So that's where now industrial AI can step in to help with some of these issues. 55 00:04:28,430 --> 00:04:42,190 The main goal, at least how we see it at Rockwell for industrial AI, is that we are going from automation systems to autonomous systems, which we heard about that a little bit today. 56 00:04:43,070 --> 00:04:53,790 So we want to move towards systems that can adapt and infer automatically to changing conditions of a plant floor without human intervention necessarily. 57 00:04:54,270 --> 00:05:08,990 We want systems then that can, using data, they can make better decisions off of that data versus somebody who has been working at a plant for 30 years and they know exactly what's wrong with their machine as we heard earlier today. 58 00:05:10,110 --> 00:05:12,350 And just generally we want to be able to help 59 00:05:13,150 --> 00:05:21,550 guide those super complex automation processes and make them easier to understand and digest with AI. 60 00:05:24,750 --> 00:05:31,670 So I'm going to talk about a little bit what is AI and what is the AI lifecycle. 61 00:05:31,670 --> 00:05:34,190 And I'm going to mostly focus on the AI lifecycle here. 62 00:05:34,909 --> 00:05:41,470 So we start with our problem definition, and I think this is super important as well, especially in the industrial automation space. 63 00:05:42,750 --> 00:05:48,310 We don't just necessarily want to be using AI or trying to use AI for AI's sake. 64 00:05:48,990 --> 00:05:52,190 We want to be able to actually define a problem. 65 00:05:52,430 --> 00:05:55,470 Maybe it's our throughput time that we're trying to solve. 66 00:05:55,870 --> 00:06:03,470 Maybe we're having something, products fail on the plant floor and we don't know why and we want to learn more information about that. 67 00:06:03,870 --> 00:06:06,150 We want to start with our problem definition. 68 00:06:06,150 --> 00:06:10,510 From there, we go into the data collection phase, then data preparation. 69 00:06:11,190 --> 00:06:13,990 And then from here, this is kind of a cycle in itself. 70 00:06:13,990 --> 00:06:17,870 So this is when we're actually creating our AI model. 71 00:06:18,190 --> 00:06:19,710 We're creating that AI model. 72 00:06:19,950 --> 00:06:21,390 We're also evaluating it. 73 00:06:21,710 --> 00:06:26,590 If we don't like how it looks, it's kind of a cycle of continuously developing and evaluating it. 74 00:06:27,390 --> 00:06:37,630 And then we move into deployment and then the actual application of that AI application into our plant. 75 00:06:39,790 --> 00:06:51,470 Some of, okay, just a note here, 80%, if you talk to any data scientist, 80% of their time is actually spent in that data preparation phase. 76 00:06:52,270 --> 00:06:58,430 So I actually, I have my MBA also from Iowa State and I have a graduate certificate in business analytics. 77 00:06:58,750 --> 00:07:06,350 So I took a lot of classes around how to create these AI models from data, from like a website or whatever. 78 00:07:08,590 --> 00:07:22,590 This was legitimately 80% of my schoolwork, was looking at the data that I pulled and evaluating it and cleaning it and figuring out if it was actually good data to put into a model. 79 00:07:23,790 --> 00:07:27,870 And that's also something that we see as a big issue on the plant floor. 80 00:07:28,430 --> 00:07:38,430 not only with data being all over the place and how the heck do we gather this data, how do we put it all together, but then is it actually good quality data for an AI model? 81 00:07:39,710 --> 00:07:49,190 Because if it's not good data, we're not going to get a good model and whatever problem we're trying to solve is not going to work out well for us. 82 00:07:52,909 --> 00:07:53,630 The other 83 00:07:54,430 --> 00:08:09,550 Maybe it's not unique to industrial automation, but I feel like it is from what I've seen on the plant floor, is how are we actually deploying these models in our factory, on our plant? 84 00:08:11,070 --> 00:08:16,190 It's unique because we're not necessarily dealing with computers all day. 85 00:08:16,830 --> 00:08:18,430 We're working with sensors on the floor. 86 00:08:18,510 --> 00:08:19,830 We're working with PLCs. 87 00:08:19,830 --> 00:08:21,390 Those are the things that's running our data. 88 00:08:21,550 --> 00:08:23,630 We have a bunch of cybersecurity 89 00:08:24,510 --> 00:08:27,950 issues and things that we need to watch out for. 90 00:08:28,750 --> 00:08:35,549 So with all of this, how are we preparing our data and then how are we actually deploying it onto our plant floor? 91 00:08:39,950 --> 00:08:48,990 So this is how we kind of see AI impacting the plant floor at Rockwell. 92 00:08:49,150 --> 00:08:51,230 So we see it first of all in three phases. 93 00:08:51,790 --> 00:09:08,990 So our design phase, actually, when we're designing our systems, whether we're an end user, whether we're an OEM, how are we coding our systems, how are we manufacturing them, how are we creating our logic to create the systems itself and then put those into our plant as a whole? 94 00:09:10,110 --> 00:09:15,230 Operations, so once that is put into the plant floor, how is that operating? 95 00:09:15,710 --> 00:09:16,870 Is there any issues with that? 96 00:09:16,870 --> 00:09:18,750 Do we need to increase throughput time? 97 00:09:18,990 --> 00:09:22,990 Whether that's production, planning, material, logistics, sensing, things like that. 98 00:09:23,230 --> 00:09:25,230 Are there issues that we need to fix for that? 99 00:09:25,550 --> 00:09:26,470 And then maintenance. 100 00:09:26,910 --> 00:09:28,910 So predictive maintenance, things like that. 101 00:09:28,910 --> 00:09:33,070 How are we monitoring our equipment once it is on the plant floor? 102 00:09:35,790 --> 00:09:38,030 So those impact 103 00:09:38,510 --> 00:09:42,110 every level of our controls operation across the plane floor. 104 00:09:42,670 --> 00:09:45,150 So at the bottom layer here, we have our equipment. 105 00:09:45,790 --> 00:09:48,950 Our second layer, we have our sensors, sensing and actuation. 106 00:09:48,950 --> 00:09:55,070 We have our IO, our end devices that are doing things, they're measuring things. 107 00:09:55,310 --> 00:10:01,150 They're then feeding into our control system that's analyzing that information and actually making things move and go burr. 108 00:10:01,950 --> 00:10:08,510 And then past that we have our operation management and then even tying into our business planning, our ERP systems, our MES systems. 109 00:10:08,910 --> 00:10:14,350 So AI also can tie into all of those layers of the technology stack as well. 110 00:10:17,790 --> 00:10:27,470 I'm going to focus on two to three of our products today that we have in our AI portfolio, but we have a lot more than that. 111 00:10:27,470 --> 00:10:30,270 And if we have time at the end, I'm happy to go through other 112 00:10:31,070 --> 00:10:32,510 things that we offer as well. 113 00:10:33,550 --> 00:10:41,310 But we do have a full stack of technology across all of those different things and across the technology stack as well. 114 00:10:43,550 --> 00:10:57,590 I'm going to probably say this a million times, but one of the main things that I love about our AI portfolio that you're going to see throughout my presentation is that our products are not necessarily built for the data scientist. 115 00:10:57,590 --> 00:10:59,910 And you don't really need a data scientist to 116 00:11:00,070 --> 00:11:00,750 implement them. 117 00:11:01,070 --> 00:11:06,510 Our products are very much focused on OT because we are originally an OT company. 118 00:11:06,910 --> 00:11:09,750 So it's really built for our automation engineer. 119 00:11:09,750 --> 00:11:11,310 It's built for the maintenance engineer. 120 00:11:11,590 --> 00:11:17,150 It's built for the kind of people that are utilizing the product and actually implementing them into the plant. 121 00:11:17,630 --> 00:11:26,670 All that machine learning stuff, all that fancy math, fancy analysis that's going on in the background, that is really done in the background of all these applications. 122 00:11:27,230 --> 00:11:28,670 So we have 123 00:11:29,550 --> 00:11:39,630 We have apps for autonomous material handling, process optimization, design environment, machine vision, industrial data ops and analytics, and predictive maintenance. 124 00:11:40,670 --> 00:11:47,870 Today I'm going to be focusing on AI-assisted design environments and adaptive process optimization. 125 00:11:50,750 --> 00:11:54,270 So the first one is in our design phase. 126 00:11:55,470 --> 00:11:57,550 How are we going to make engineering faster? 127 00:11:57,550 --> 00:12:04,670 How can we make it easy to understand for these, maybe there's new people coming in that have never worked in industrial automation before. 128 00:12:05,870 --> 00:12:09,710 Or so how are we generating and refining code more efficiently? 129 00:12:10,190 --> 00:12:11,950 How are we documenting code? 130 00:12:12,270 --> 00:12:15,630 I mean, engineers, they love to write code, but they hate documenting it. 131 00:12:15,630 --> 00:12:18,030 So we can utilize AI to actually do that for us. 132 00:12:18,030 --> 00:12:19,150 So that's really awesome. 133 00:12:19,550 --> 00:12:26,910 And then also reducing that onboarding time for our new people that are coming into the plant in this world. 134 00:12:28,510 --> 00:12:35,310 So Factory Talk Design Studio Copilot is the first thing I'm going to talk about today. 135 00:12:35,710 --> 00:12:39,710 Design Studio is our Studio 5000. 136 00:12:40,190 --> 00:12:41,310 but it's in the cloud. 137 00:12:42,830 --> 00:12:47,070 So it is able to code our controllers. 138 00:12:48,350 --> 00:12:54,110 One of the two things that's really cool about Design Studio is that it does have copilot capability. 139 00:12:54,750 --> 00:12:57,390 That's one of the demos, that's my live demo for today. 140 00:12:57,790 --> 00:13:04,110 So if it works, the two things that it can be really good at is product guidance and project creation. 141 00:13:04,590 --> 00:13:08,990 So what we're going to see is I'm going to show you code and 142 00:13:10,190 --> 00:13:12,510 And I'm going to say, I don't know what this code is doing. 143 00:13:13,150 --> 00:13:14,030 I'm in sales now. 144 00:13:14,310 --> 00:13:15,550 I'm not a technical person. 145 00:13:15,790 --> 00:13:17,350 Can you explain to me what this code is doing? 146 00:13:17,350 --> 00:13:21,230 It's going to give us a really good description of what that code is doing. 147 00:13:22,110 --> 00:13:26,830 And a couple of other things they can do if code is faulting out for whatever reason. 148 00:13:27,070 --> 00:13:35,070 Copilot can help show you what that fault is and what it means and explain to our designer what it means. 149 00:13:35,550 --> 00:13:41,230 And then it also actually has the ability to do code creation, which is going to be huge. 150 00:13:42,190 --> 00:13:46,870 It's not, again, it's AI, so it's still learning. 151 00:13:46,870 --> 00:13:48,030 We're still developing it. 152 00:13:48,990 --> 00:13:51,630 but it can actually go in and create code. 153 00:13:51,630 --> 00:14:12,590 And if really, really looking into the future, something really cool that you could do with it, if you have code standards, if you have a library, you could bring that library into Copilot or into Design Studio and then say, computer, Copilot, code me a new line based on my standards. 154 00:14:13,270 --> 00:14:16,670 And it will be able to do all of that for you, which is super awesome. 155 00:14:19,470 --> 00:14:24,350 Okay, next thing I'm going to talk about, has anybody heard of this Factory Talk Optics? 156 00:14:26,270 --> 00:14:31,390 Okay, this is our newest visualization platform. 157 00:14:32,190 --> 00:14:36,110 It's similar to our ViewME in our ViewSE softwares. 158 00:14:36,590 --> 00:14:40,350 It does visualization, so it's a machine edition currently. 159 00:14:40,430 --> 00:14:43,470 It's going to be a full plant SCADA version very soon. 160 00:14:44,430 --> 00:14:47,950 But it's also really good for data analysis and data transfer as well. 161 00:14:47,950 --> 00:14:51,150 But I'm mostly going to focus on the visualization aspect of it. 162 00:14:54,070 --> 00:14:54,510 Whoa. 163 00:14:56,590 --> 00:14:57,150 There it goes. 164 00:14:57,470 --> 00:14:57,630 Okay. 165 00:14:59,310 --> 00:15:02,110 I am so excited about this. 166 00:15:02,430 --> 00:15:06,270 So one of the new things that were coming out, this is not out yet. 167 00:15:06,270 --> 00:15:10,990 Marketing's probably going to hate me for even bringing it up, but I'm very excited about it. 168 00:15:11,790 --> 00:15:13,990 is this AI design assistance. 169 00:15:14,350 --> 00:15:19,870 So similar to Design Studio Copilot, we're bringing that into Optics as well. 170 00:15:19,870 --> 00:15:22,990 So this is going to give us the ability to do 2 main things. 171 00:15:23,550 --> 00:15:27,310 The first one is taking a picture. 172 00:15:27,470 --> 00:15:32,030 So you have an idea for an HMI in your mind. 173 00:15:32,110 --> 00:15:33,150 You can sketch that out. 174 00:15:33,470 --> 00:15:38,910 Or if you're converting from another HMI platform, you can take a screenshot of that 175 00:15:39,750 --> 00:15:53,629 Plug it into Optics, and the Design Studio will be able to create those graphics automatically for you, as well as create the objects that go along with that screen as well. 176 00:15:54,989 --> 00:15:59,069 Similar to Design Studio, it's also going to have a Copilot capability. 177 00:16:00,109 --> 00:16:04,669 So again, being able to, hey, can you create a database for me? 178 00:16:05,549 --> 00:16:13,389 take tags XYZ, I want to plot those and it will create that for you, as well as just general design advice and assistance. 179 00:16:16,829 --> 00:16:23,309 Okay, the next thing I'm going to focus on is adaptive process optimization. 180 00:16:24,349 --> 00:16:28,029 So the main things with this is we're looking at our control level now. 181 00:16:28,189 --> 00:16:33,429 How can we tighten our controls up when it comes to our process to 182 00:16:34,429 --> 00:16:48,589 to have better quality, to increase throughput time, doing that without necessarily a sensor or human intervention, that's what this process optimization is all about. 183 00:16:49,629 --> 00:16:54,669 So with that, the product that goes along with that solution is Logix AI. 184 00:16:55,469 --> 00:17:01,069 So this is also, this is my favorite product out of our AI portfolio. 185 00:17:01,789 --> 00:17:06,909 So this runs either on an industrial computer or we have a module. 186 00:17:06,909 --> 00:17:14,029 If you have control logics in your floor, there's a module that you can plug into your control logics chassis that can run on this as well. 187 00:17:14,589 --> 00:17:18,669 I have a video for this as well, so I'm going to show you what it actually looks like. 188 00:17:18,829 --> 00:17:24,429 But the two main things that logics AI can do is anomaly detection. 189 00:17:24,749 --> 00:17:28,269 So being able to detect that something is out 190 00:17:28,909 --> 00:17:33,949 something looks like an anomaly before a human would necessarily be able to see that. 191 00:17:34,269 --> 00:17:36,669 The other thing it can do is act as a soft sensor. 192 00:17:37,869 --> 00:17:51,709 So it's using the data that we're feeding in to the model and it's predicting what a value, maybe a value that's really hard to find from a traditional sensor is actually at. 193 00:17:55,069 --> 00:17:58,109 So how this works, and you'll see this in the video as well. 194 00:17:58,189 --> 00:18:03,709 So we connect and import our controller tanks from our controller into the Logix AI software. 195 00:18:04,509 --> 00:18:06,029 We configure our model. 196 00:18:06,029 --> 00:18:09,789 So let's say, for example, we have an oven line. 197 00:18:10,429 --> 00:18:11,469 We're baking cookies. 198 00:18:12,189 --> 00:18:15,709 I want to measure the dryness of those cookies as it's coming out of the oven. 199 00:18:16,109 --> 00:18:20,829 Obviously, really hard to do that unless I'm grabbing it off the line and taking a quality test there. 200 00:18:21,829 --> 00:18:29,149 So I'm going to implement a Logics AI example, and I'm going to say, these are the things that I think are impacting this model. 201 00:18:29,549 --> 00:18:38,749 The speed of the line, the ambient temperature, the temperature of the oven, tags that we already are getting those examples from, we're going to plug into that model. 202 00:18:39,549 --> 00:18:44,829 Logics AI will say, beep, bop, boop, beep, machine learning stuff in the background. 203 00:18:45,629 --> 00:18:47,789 Here is your AI model. 204 00:18:48,189 --> 00:18:50,549 It has an 80% accuracy or whatever. 205 00:18:50,549 --> 00:18:51,829 You can make a threshold for that. 206 00:18:51,829 --> 00:18:55,469 And I'll say, yep, that looks good to me. 207 00:18:55,869 --> 00:18:57,309 Thank you, Logix AI. 208 00:18:57,309 --> 00:19:05,629 So then I can import that model back into my controller to close that loop so it will start predicting in real time then. 209 00:19:08,669 --> 00:19:11,309 So these are some use cases for Logix AI. 210 00:19:11,869 --> 00:19:17,869 It does use first principle physics as well to create that AI model. 211 00:19:18,509 --> 00:19:32,269 So the first example here is we have a rolled product like steel, paper, what this machine was doing, it rolls that product until it gets to a defined spot. 212 00:19:32,949 --> 00:19:36,029 An issue is that it was moving really, really fast. 213 00:19:36,269 --> 00:19:42,749 So the sensor that they had measuring these roles, it would lose integrity and it wouldn't be able to measure that anymore. 214 00:19:43,309 --> 00:19:57,949 So then they implemented Logix AI and they put in all of their historical data and they were able to, if those sensors, if they lost their values, they were able to utilize Logix AI instead in order to kind of tune in that PID. 215 00:20:01,789 --> 00:20:03,309 The next one is freeze drying. 216 00:20:03,309 --> 00:20:09,269 So this is a food and beverage example or the cookies example. 217 00:20:09,269 --> 00:20:15,789 Like I was saying before, it was really difficult to measure the moisture content of the product during freeze drying. 218 00:20:16,189 --> 00:20:20,909 So what they were able to do is, again, they were using Logics AI in the soft sensor scenario. 219 00:20:21,389 --> 00:20:31,669 They were able to take in that live data that was coming from the controller, train their model, predict what that moisture content was at, and then utilize that 220 00:20:31,749 --> 00:20:36,349 again just tune in that PID loop to help the quality of their process. 221 00:20:38,429 --> 00:20:39,549 This is the last one here. 222 00:20:39,549 --> 00:20:43,469 So this is the other use case for Logix AI, so anomaly detection. 223 00:20:44,669 --> 00:20:47,549 So this was a tire manufacturer. 224 00:20:47,869 --> 00:20:53,229 They were, sorry. 225 00:20:53,749 --> 00:20:54,989 doing tire splicing. 226 00:20:55,149 --> 00:20:58,669 So these tire splices had to be super, super accurate. 227 00:20:58,669 --> 00:21:03,149 They didn't have that big of a tolerance that they could really go off of. 228 00:21:03,629 --> 00:21:16,349 So again, utilizing Logix AI, they were able to take in whatever data points that they thought were applicable to their process and then put that in to their controller. 229 00:21:16,669 --> 00:21:22,189 And then they were able to analyze if that tire splice was going out of anomaly. 230 00:21:22,909 --> 00:21:29,389 or going into an anomaly, they were tracking the position of that tire splice. 231 00:21:29,429 --> 00:21:38,429 And so if it even went off a little bit of their tolerance, they were able to go in and check their process and set up and fix whatever they needed to. 232 00:21:41,389 --> 00:21:44,749 Okay, I'm gonna show you some demos now. 233 00:21:45,789 --> 00:21:47,549 Is there any, how much time do I have? 234 00:21:47,549 --> 00:21:48,989 Okay, we got 20 minutes, perfect. 235 00:21:48,989 --> 00:21:51,389 Is there any questions that I can answer 236 00:21:51,869 --> 00:21:58,989 While I'm pulling these up, the first example was... 237 00:22:00,589 --> 00:22:01,229 Rolling. 238 00:22:02,589 --> 00:22:02,789 Yeah. 239 00:22:07,149 --> 00:22:08,629 I tried to get a live demo. 240 00:22:08,629 --> 00:22:10,109 Oh wait, no, that's not the right one. 241 00:22:17,529 --> 00:22:17,929 Okay. 242 00:22:20,569 --> 00:22:29,129 I tried to get a live demo of this as well, but our training course instances was not agreeing with me the past couple of days, so I was not able to. 243 00:22:29,129 --> 00:22:31,849 So I'm going to be clicking through here. 244 00:22:32,329 --> 00:22:32,649 Okay. 245 00:22:34,029 --> 00:22:40,349 So when you open up Logix AI, this is the first screen that you're going to see. 246 00:22:40,909 --> 00:22:45,309 You are defining your prediction and connecting to your control module. 247 00:22:45,949 --> 00:22:56,909 From there, what they're doing now, once they're connected to their controller, they're selecting those inputs that they think are impacting the process of whatever output they are trying to predict. 248 00:22:57,629 --> 00:23:00,669 You're also able to, in the first screen here, 249 00:23:01,669 --> 00:23:02,589 I'm going to go back. 250 00:23:07,069 --> 00:23:20,829 So you can either do a manual algorithm or we actually have pre-built in ones as well for boilers, generators, and pumps if there is a specific piece of equipment that you're looking to monitor. 251 00:23:23,149 --> 00:23:28,549 So right now they're selecting those tags, and they are going to select the tags that they think are affecting those processes. 252 00:23:28,549 --> 00:23:33,869 So these are our input tags at the bottom here, and they're also selecting their output variable. 253 00:23:33,949 --> 00:23:36,749 So the thing that they are trying to predict. 254 00:23:39,149 --> 00:23:43,229 From there, they also set limits for those tags. 255 00:23:43,229 --> 00:23:46,909 That's very important for Logix AI to do as well. 256 00:23:46,949 --> 00:23:48,589 I'm going to pause on this screen here. 257 00:23:50,429 --> 00:23:52,029 It's just going to give you a summary. 258 00:23:53,269 --> 00:23:54,909 Again, we have our output tag. 259 00:23:54,909 --> 00:23:58,429 They're trying to predict the mass flow of their model and our inputs. 260 00:23:58,429 --> 00:24:04,909 They have a running, they have a speed, they have a running tag, and a couple of other, I don't know what the other ones do, but those are their input tags. 261 00:24:04,909 --> 00:24:10,229 And then they're putting limits on those tags, which Logics AI does need those limits to be able to evaluate. 262 00:24:10,229 --> 00:24:13,709 And they're going to finish that up. 263 00:24:20,099 --> 00:24:23,059 And then it did not show it in here, but 264 00:24:27,069 --> 00:24:30,029 They also created the prediction during this time as well. 265 00:24:30,429 --> 00:24:45,789 For the model, they're exporting that prediction, and then they're going, or exporting that model, they're putting it back into their actual Studio 5000 into their code, their logics file. 266 00:24:46,629 --> 00:24:48,269 I'll skip that, it's showing the inputs. 267 00:24:48,669 --> 00:24:51,869 And then also kind of the cool thing about 268 00:24:54,429 --> 00:25:04,829 Logix AI, if you're familiar with our HMI faceplates, we do have the ability to tie directly into an HMI as well with the ViewME or USC software. 269 00:25:07,389 --> 00:25:14,589 I don't know if they have a trend in here, but yeah. 270 00:25:17,509 --> 00:25:17,869 Okay. 271 00:25:21,309 --> 00:25:24,589 So I just wanted to give you guys a taste of what that software actually looked like. 272 00:25:30,269 --> 00:25:31,069 Design Studio. 273 00:25:31,309 --> 00:25:34,269 I was hoping this won't close, but it might take a little bit to open. 274 00:26:08,189 --> 00:26:10,429 Live demos are always really fun. 275 00:26:26,989 --> 00:26:30,869 Yes, there was a manual option on there, like an open option. 276 00:26:30,869 --> 00:26:34,789 Is there like a standard you follow on that? 277 00:26:36,749 --> 00:26:38,509 Not necessarily. 278 00:26:38,749 --> 00:26:45,869 I will say it does have to be like some kind of physical system. 279 00:26:46,429 --> 00:26:51,469 The other example that I didn't put in this PowerPoint is called perfect fill. 280 00:26:51,709 --> 00:27:01,469 So it was another quality thing where they were just like a little bit out of tolerance or they were really trying to zone in on their fill level on a bottle. 281 00:27:01,949 --> 00:27:04,829 So then they were using that fill level as their output. 282 00:27:05,629 --> 00:27:09,469 And then whatever inputs they put in, I'm not really sure. 283 00:27:09,469 --> 00:27:18,229 Can you bring your natural instruments or all of the map works into it and then hook it up? 284 00:27:19,589 --> 00:27:25,309 What can you-- Oh, simulink and natural instruments is like if you model physical systems. 285 00:27:25,629 --> 00:27:29,549 Oh, that's a good question. 286 00:27:29,949 --> 00:27:30,749 I'm not sure. 287 00:27:31,149 --> 00:27:33,149 So we do have-- 288 00:27:34,269 --> 00:27:36,949 We have a software as well that's our digital twin. 289 00:27:36,949 --> 00:27:38,349 It's called Emulate 3D. 290 00:27:38,349 --> 00:27:40,749 So it might work with that specifically. 291 00:27:40,749 --> 00:27:44,429 I'm not sure about any other kind of software. 292 00:27:45,949 --> 00:27:46,349 Yes. 293 00:27:50,269 --> 00:27:52,749 Can I answer any other questions while this opens? 294 00:27:52,749 --> 00:27:53,149 Yes. 295 00:28:15,509 --> 00:28:16,949 That's a really good question. 296 00:28:18,869 --> 00:28:26,709 I just think the ability to just realize the tools that are out there or what's coming, that's what's really important. 297 00:28:27,029 --> 00:28:28,309 To be honest, 298 00:28:29,789 --> 00:28:37,229 In industrial automation specifically, there are companies that are really looking ahead in the future and trying to implement these things. 299 00:28:37,229 --> 00:28:38,829 Pella is a great example. 300 00:28:39,229 --> 00:28:44,829 However, I'm still seeing a lot of plants that are still running on PLCs from the 50s and 60s. 301 00:28:45,549 --> 00:28:56,269 So I just feel like industrial automation as a whole, as an industry, we are a little bit behind the game, I guess, when it comes to adapting these newer technologies. 302 00:28:57,029 --> 00:28:57,549 But just 303 00:28:58,189 --> 00:29:01,869 being aware that they do exist and that they're out there. 304 00:29:06,269 --> 00:29:06,549 Yeah. 305 00:29:07,789 --> 00:29:08,509 Exactly. 306 00:29:09,309 --> 00:29:09,509 Yeah. 307 00:29:13,949 --> 00:29:14,429 Okay. 308 00:29:17,629 --> 00:29:21,709 I'll add onto that a little bit before we get into this. 309 00:29:22,109 --> 00:29:27,229 I wasn't originally planning on getting my business analytics certificate at all. 310 00:29:28,589 --> 00:29:34,989 But then it ended up being the best classes that I took for my career. 311 00:29:38,189 --> 00:29:43,709 for what I'm doing today, mostly because I am focusing on our info software here. 312 00:29:44,349 --> 00:29:49,389 But just being able to actually understand as well how those algorithms are working in the background. 313 00:29:50,389 --> 00:29:54,149 That's helped me understand then how this software is at least functioning. 314 00:29:54,149 --> 00:30:01,789 It's like I don't need to be doing any of that data scientist, data analyst stuff, but at least I understand how it is functioning in the background. 315 00:30:02,589 --> 00:30:02,709 Yeah. 316 00:30:02,709 --> 00:30:25,149 I tell my students that I don't think that AI is going to replace engineers anytime soon, but how to use AI are going to replace 317 00:30:26,349 --> 00:30:26,989 Exactly. 318 00:30:26,989 --> 00:30:28,149 Yeah, I would agree with that. 319 00:30:35,299 --> 00:30:35,619 Yeah. 320 00:30:36,339 --> 00:30:36,499 Yeah. 321 00:30:37,059 --> 00:30:37,459 Yes. 322 00:30:48,739 --> 00:30:49,299 Sorry. 323 00:30:51,379 --> 00:30:58,179 So I'm going to show it can it can help build it is this is this is our so 324 00:30:59,069 --> 00:31:01,309 Logix AI was my machine learning example. 325 00:31:01,629 --> 00:31:03,029 So it's taking in that data. 326 00:31:03,029 --> 00:31:09,229 It's creating a physical like math algorithm out of the data that we fed it to predict an output. 327 00:31:09,789 --> 00:31:10,989 This is our example of Gen. 328 00:31:10,989 --> 00:31:11,309 AI. 329 00:31:11,309 --> 00:31:13,469 We're going to do one question. 330 00:31:13,469 --> 00:31:15,109 I just want to make sure they end up on recording. 331 00:31:16,429 --> 00:31:17,069 Oh, OK. 332 00:31:17,789 --> 00:31:19,829 Can you say that you're automating the source? 333 00:31:20,029 --> 00:31:24,979 You put it in? 334 00:31:25,299 --> 00:31:25,779 Yes. 335 00:31:26,099 --> 00:31:26,499 Yes. 336 00:31:27,859 --> 00:31:31,579 And that's training your model is most of the effort. 337 00:31:38,669 --> 00:31:39,069 Yes. 338 00:31:40,189 --> 00:31:42,709 So that's what Logix AI was doing. 339 00:31:42,709 --> 00:31:44,189 It was taking in those inputs. 340 00:31:44,269 --> 00:31:52,109 It was cleaning the data in the background, doing that analysis, and then coming out with a model that we can plug back into our system. 341 00:31:55,149 --> 00:31:56,429 This is Design Studio. 342 00:31:57,149 --> 00:32:01,629 So this is where we're going to talk about our generative AI example. 343 00:32:01,629 --> 00:32:03,629 I'm really bad at saying that word, obviously. 344 00:32:03,949 --> 00:32:08,029 So you can see here that I have all of this code. 345 00:32:08,109 --> 00:32:10,429 And again, I'm in sales now. 346 00:32:10,429 --> 00:32:11,709 I'm not a technical person. 347 00:32:11,709 --> 00:32:14,669 I have no idea what this is doing. 348 00:32:15,069 --> 00:32:16,589 So I'm going to ask Copilot. 349 00:32:16,589 --> 00:32:20,189 I did try this a little bit earlier and it did need a specific 350 00:32:22,589 --> 00:32:23,749 task to look at. 351 00:32:23,749 --> 00:32:30,789 So I'm going to say, what is going on with routine SIP? 352 00:32:47,929 --> 00:32:50,089 This might take a little bit to analyze. 353 00:32:50,089 --> 00:32:53,049 I did already run this through, so we'll wait for it. 354 00:32:54,009 --> 00:32:58,529 But I said, what does this code do? 355 00:32:58,529 --> 00:33:00,049 And it said you're not being specific enough. 356 00:33:00,069 --> 00:33:02,429 Dominique, I need a better example than that. 357 00:33:02,909 --> 00:33:05,949 So then I said, okay, what is this piece of code doing? 358 00:33:06,149 --> 00:33:13,869 And you can see here, I won't read through all of it, but it does a really, really good job at documenting what that piece of code is doing. 359 00:33:13,869 --> 00:33:18,349 So it even told me it could go through it line by line and I was like, no, thank you. 360 00:33:18,669 --> 00:33:23,229 But it's saying I have my output. 361 00:33:23,549 --> 00:33:25,469 It's a pump output control pretty much. 362 00:33:25,949 --> 00:33:28,589 It is requesting feedback and then it's 363 00:33:29,309 --> 00:33:30,989 Yeah, it summarized it. 364 00:33:30,989 --> 00:33:42,269 So it says it provides a manual on off auto mode, drives a single pump DO channel based on the auto demand, and then it sends a request done once that code is done through. 365 00:33:42,589 --> 00:33:50,349 So again, if your engineers really, really, really don't like documenting code, this is a really good way to summarize that. 366 00:33:50,349 --> 00:33:56,989 Or in my case, if you have a creative coder, me, I'm a creative coder, 367 00:33:57,869 --> 00:34:01,469 It can help just kind of debug and actually tell you what's going on with that code. 368 00:34:05,069 --> 00:34:09,549 Okay, I did have a prompt that I'm going to put in here. 369 00:34:10,349 --> 00:34:12,989 So this is the other thing, the Gen. 370 00:34:12,989 --> 00:34:13,469 AI. 371 00:34:13,789 --> 00:34:17,309 So I'm going to ask it to create a new smart object definition. 372 00:34:17,748 --> 00:34:19,549 I'm giving it a couple of tags. 373 00:34:21,309 --> 00:34:24,109 and just telling them name it whatever they want. 374 00:34:24,509 --> 00:34:29,949 And then in the main routine, oh, it does not have a program A, so I'm wondering if it will throw a flag or create one. 375 00:34:30,989 --> 00:34:35,549 It's going to provide logic for a fault light output and a reset button. 376 00:34:35,789 --> 00:34:40,429 I have not tried this yet, so we'll see how it goes. 377 00:34:40,989 --> 00:34:50,109 And then after this, I'm also open to taking, if anybody has a prompt that they want to throw in, we can see if it 378 00:34:51,309 --> 00:34:53,069 outputs what we need it to. 379 00:34:56,109 --> 00:35:00,349 While that is going, we'll multitask a little here. 380 00:35:00,829 --> 00:35:08,109 I know I didn't talk, again, I just focused on two of the many softwares that we have. 381 00:35:08,749 --> 00:35:13,709 Is there any specific thing on our plant floor here? 382 00:35:14,349 --> 00:35:14,669 Yes. 383 00:35:14,749 --> 00:35:18,229 I'd be curious to hear more about your predictive maintenance. 384 00:35:18,509 --> 00:35:19,149 Of course. 385 00:35:24,429 --> 00:35:29,389 So when it comes to predictive maintenance, we have one software that's currently out. 386 00:35:29,869 --> 00:35:31,949 It is called, I'm going to go back into present. 387 00:35:31,949 --> 00:35:33,709 Can everybody see that okay? 388 00:35:34,829 --> 00:35:35,309 No. 389 00:35:36,629 --> 00:35:36,789 Okay. 390 00:35:41,069 --> 00:35:41,189 Yes. 391 00:35:41,189 --> 00:35:41,909 Okay, good. 392 00:35:44,429 --> 00:35:47,109 This is our main out-of-the-box software. 393 00:35:47,109 --> 00:35:48,749 It's called Guardian AI. 394 00:35:51,469 --> 00:35:56,589 What it's meant to do is monitor the physical assets that you have on the plant floor. 395 00:35:56,909 --> 00:36:01,669 So the main ones that are built in are pumps, motors, blowers, and fans. 396 00:36:03,229 --> 00:36:10,749 It is currently only compatible with our PowerFlex 755 line of drives. 397 00:36:11,149 --> 00:36:13,189 We have a new line coming out, the 525s. 398 00:36:13,189 --> 00:36:14,589 It will also be compatible with that. 399 00:36:14,909 --> 00:36:16,229 But it uses that drive. 400 00:36:16,229 --> 00:36:19,149 It's using some of the high availability data 401 00:36:19,869 --> 00:36:20,909 from the firmware. 402 00:36:21,229 --> 00:36:28,749 And it's doing, again, fancy math, it's a four year analysis on there to look at that drive signature. 403 00:36:28,989 --> 00:36:34,189 It's creating a baseline utilizing clustering, utilizing an AI algorithm. 404 00:36:34,509 --> 00:36:44,669 And then from there it's able to detect an anomaly before it's necessarily seen by an operator or before an asset actually fails. 405 00:36:44,989 --> 00:36:46,349 So it will send out an alert. 406 00:36:47,069 --> 00:36:51,629 through your HMI or through e-mail to tell you, hey, let's say we use a fan. 407 00:36:52,029 --> 00:36:55,309 Hey, I think fan one is failing right now. 408 00:36:56,109 --> 00:37:02,829 And it also has embedded first principle faults in there as well. 409 00:37:03,229 --> 00:37:08,029 So it won't only tell you, hey, I think your fan is failing or I'll use a pump. 410 00:37:08,029 --> 00:37:10,189 It won't only tell you, hey, I think your pump is failing. 411 00:37:10,509 --> 00:37:12,669 It will say, hey, I think your pump is cavitating. 412 00:37:13,229 --> 00:37:15,469 You should go check on that or have somebody check on that. 413 00:37:17,789 --> 00:37:18,189 Yes. 414 00:37:18,589 --> 00:37:20,029 Using a fan as an example. 415 00:37:21,309 --> 00:37:22,029 Oh, sorry. 416 00:37:22,909 --> 00:37:23,389 Sorry. 417 00:37:24,429 --> 00:37:24,709 Yeah. 418 00:37:26,429 --> 00:37:26,749 Go. 419 00:37:27,309 --> 00:37:28,269 No, go ahead. 420 00:37:28,509 --> 00:37:33,309 Using a fan as an example, what specific sort of items is it monitoring on the fan? 421 00:37:33,389 --> 00:37:35,669 You know, vibration, heat, voltage draw. 422 00:37:36,669 --> 00:37:41,629 It's only, the only data that it's using is the three-phase current that's coming from the drive. 423 00:37:42,429 --> 00:37:43,949 Yes, we are. 424 00:37:43,949 --> 00:37:53,869 We're coming out with a new vibration module soon, and that will be able to tie into Guardian AI, but we don't have the ability to specifically do vibration monitoring right now. 425 00:38:02,069 --> 00:38:03,109 Sorry, can you repeat that? 426 00:38:16,169 --> 00:38:17,129 I don't have. 427 00:38:17,929 --> 00:38:20,489 Oh, the question was is 428 00:38:20,909 --> 00:38:28,189 Is AI a better way to monitor these systems than traditional monitoring, like looking for temperature spike, vibration spike, et cetera? 429 00:38:30,269 --> 00:38:46,349 Potentially, the thing with Guardian AI, for example, is that it might be able to catch those spikes faster than your traditional monitoring before something actually fails and then you're retrospect looking like, oh, hey, what's going on there? 430 00:38:49,709 --> 00:38:51,229 Any other five minutes? 431 00:38:51,229 --> 00:38:53,069 Okay, let's go back here. 432 00:39:02,259 --> 00:39:04,339 Let's see, do we have a program A? 433 00:39:09,619 --> 00:39:10,579 Yeah, go ahead. 434 00:39:12,219 --> 00:39:15,619 Is there no bolt on option or is it Rockwell Automation? 435 00:39:17,539 --> 00:39:19,539 It's just Rockwell Automation. 436 00:39:31,429 --> 00:39:34,109 It said it created it, but I'm not seeing anything. 437 00:39:43,189 --> 00:39:44,229 Do we see? 438 00:39:45,749 --> 00:39:47,029 Oh, smart objects. 439 00:39:48,709 --> 00:39:49,909 Okay, well that worked well. 440 00:39:55,429 --> 00:39:56,629 Yeah, exactly. 441 00:40:01,429 --> 00:40:01,989 Let's see. 442 00:40:07,189 --> 00:40:15,509 What's your arrangement with time and hours? 443 00:40:17,469 --> 00:40:20,589 You or your team, or how's that commercial? 444 00:40:20,589 --> 00:40:21,789 That's a great question. 445 00:40:21,789 --> 00:40:30,429 I'm going to, while that's working, and while I'm actually trying to get my demos to work, I will go on to this last slide here. 446 00:40:34,749 --> 00:40:34,949 Okay. 447 00:40:35,869 --> 00:40:36,749 Fantastic question. 448 00:40:36,749 --> 00:40:39,949 So asked on the commercial side, what does the team look like? 449 00:40:39,949 --> 00:40:40,909 What do partners look like? 450 00:40:40,909 --> 00:40:41,629 Things like that. 451 00:40:42,589 --> 00:40:45,309 We have a great partner network at Rockwell. 452 00:40:45,629 --> 00:40:51,469 So if you're familiar with Van Meter, they are our authorized distributor in Iowa. 453 00:40:51,789 --> 00:40:53,869 They have fantastic resources. 454 00:40:53,869 --> 00:40:55,629 They do a bunch of classes. 455 00:40:56,589 --> 00:41:01,229 They have their complete own team of software specialist, account managers, things like that. 456 00:41:02,189 --> 00:41:09,549 that can help you pick whatever softwares or if you have any specific problems you're trying to solve, they're great to reach out to. 457 00:41:10,189 --> 00:41:15,429 We do have teams at Rockwell, so I actually am no longer a technology consultant. 458 00:41:15,429 --> 00:41:17,469 I just switched roles to become an account manager. 459 00:41:18,109 --> 00:41:21,069 So I'm focused on industry in Iowa here now. 460 00:41:21,549 --> 00:41:29,789 But any of our technology consultants, we do have teams on the software control side and on our intelligent device, so drives and things like that as well. 461 00:41:30,349 --> 00:41:31,909 We have a couple of resources in Iowa 462 00:41:32,509 --> 00:41:35,869 happy to come in, talk to you. 463 00:41:35,869 --> 00:41:43,149 We're free, at least to start, to just talk you through solutions and things like that. 464 00:41:44,269 --> 00:41:47,909 System integrators, we also have a ton of great system integrators that we're partnered with. 465 00:41:49,069 --> 00:41:57,069 In Iowa, interstates is going to be our biggest one here, so they're also great partners with us with our technology when it comes to adapting these kinds of things. 466 00:41:59,229 --> 00:42:01,389 Did that answer your question okay? 467 00:42:02,189 --> 00:42:02,709 I think so. 468 00:42:02,709 --> 00:42:10,279 It sounded like the logics 5,000 on hand. 469 00:42:10,279 --> 00:42:10,439 Yeah. 470 00:42:11,359 --> 00:42:15,759 And see what we have and then you'll come up with under 80. 471 00:42:15,759 --> 00:42:15,919 Yeah, 100%. 472 00:42:15,919 --> 00:42:19,159 Yeah, I do have business cards up here. 473 00:42:19,559 --> 00:42:23,479 So feel free to take any, reach out to me. 474 00:42:23,479 --> 00:42:24,639 I can help you. 475 00:42:24,639 --> 00:42:29,159 At least get to the right resources if I'm not necessarily the right resource. 476 00:42:30,919 --> 00:42:32,839 But how much time do I have? 477 00:42:32,959 --> 00:42:34,319 About one minute if you have any rapid. 478 00:42:36,509 --> 00:42:38,989 My wrap up is seeing if I can get this to work. 479 00:42:44,269 --> 00:42:44,829 Okay. 480 00:42:57,339 --> 00:42:58,299 It's putting me somewhere. 481 00:42:58,299 --> 00:43:00,099 I just don't know where it's putting it. 482 00:43:02,139 --> 00:43:03,659 I should have started with a fresh project. 483 00:43:04,259 --> 00:43:05,019 That's okay. 484 00:43:05,099 --> 00:43:05,739 Live demos. 485 00:43:08,219 --> 00:43:08,499 Yeah. 486 00:43:09,789 --> 00:43:10,269 Feel free. 487 00:43:10,269 --> 00:43:11,869 I'll be here probably until three. 488 00:43:11,869 --> 00:43:18,429 I have to head to Milwaukee after this, but come up, talk to me, ask me any questions, grab a business card, reach out to me. 489 00:43:19,229 --> 00:43:26,589 Just at the end of the day, I just wanted you guys to know that like with all of our AI technology, again, we're really built for OT. 490 00:43:26,749 --> 00:43:27,629 So we're here to help. 491 00:43:27,629 --> 00:43:30,349 We're here to help you guys along your AI journey. 492 00:43:32,109 --> 00:43:32,669 Thank you.