AI enables the future of data driven manufacturing Podcast – Transcript
In a recent podcast episode, host Spencer Acain is joined by Ralf Wagner, Senior Vice President of data driven manufacturing at Siemens, to discuss the importance of tools like Siemens Insights Hub for smart manufacturing. Additionally, he will examine the key role AI is playing in these types of tools and why it will be crucial in achieving the next step in smart manufacturing.
Check out the full episode here or keep reading for the full transcript.
Spencer Acain:
Hello and welcome to the AI Spectrum Podcast. I’m your host, Spencer Acain. In this series, we explore a wide range of AI topics from all across Siemens and how they are applied to different technologies. Today I’m joined by Ralf Wagner, senior vice president of Data-Driven Manufacturing at Siemens. Welcome, Ralf.
Ralf Wagner:
Thanks Spencer for having me.
Spencer Acain:
All right, before we jump into this, can you give me a brief overview of your background and your work at Siemens?
Ralf Wagner:
Yeah, happy to do so. Actually, I’m a longtime Siemens employee, so I’m in my year 25 now with Siemens. Mostly I spent that in industry software and the environment of everything, which has to do with manufacturing specific software coming from the shop floor and going up now to the cloud. So I had the pleasure to be part of that IoT data and analytics journey almost from the very beginning, which was now in 2015, 2016, in various positions. Overall in my Siemens career, I spent time in the U.S. I spent time in Malaysia working for the company. So I got some experience abroad, different cultures and working styles, but as we are a global company, which I highly enjoy. So also today and today I’m responsible for Insights Hub, which is our data-driven manufacturing and IoT analytics solution. I have this responsibility now driving that business with the global team in the U.S in Europe as well as in India and China now since two years under my responsibility, but being part of that business and that team since a longer time already.
Spencer Acain:
Wow. Sounds like you’ve had quite an extensive career in the IoT manufacturing and smart industry all across the world. So can you tell me a little bit more about what Insights Hub is and how it’s leveraging artificial intelligence and machine learning?
Ralf Wagner:
Happy to do so. So what we call today Insights Hub is actually our data-driven manufacturing solution. So we help with this solution, our customers to use their data from their equipment and their OT, operation technology systems, mainly from the shop floor to get and generate actionable insights, which actually helps them to improve their decision-making for production every day. So with that, actually looking at the bigger picture of smart manufacturing, which is way more, it’s basically manufacturing engineering, it’s manufacturing execution and manufacturing optimization. So that optimization is a major element of what we call the smart manufacturing digital thread. And every customer today has some kind of continuous improvement process which they have in place, whether this is DMIC, whether it is Six Sigma, whether it’s something else when they meet on the shop floor every morning or in the shift handover, they look back what worked in the last shift, what didn’t go that well, were there repeating issues where they want to go down to the root causes and actually find out what to improve.
And this is a gradual continuous improvement each and every day on the shop floor. But mostly, and this is also not only what we see in the market with our customers, but also McKinsey and Boston Consulting had a study a few years back. Mostly this is still done with pen and paper, with Excel spreadsheet, on whiteboards, and there is a systematic process to it, but there is not a systematic approach to the data and what is available on the shop floor in order to take advantage of this. So we enable those customers to make this continuous improvement process way more effect and data driven. So you come to root causes and to the issues way faster than just leaning on experts and on personnel and what they have seen before, but also to deal with the situation and constellations which have not been appeared before to get to decisions which help you to improve your production and you can improve your production in multiple ways depending on your priority.
Some might improve for lower costs, some might improve for higher speed, some might improve for higher quality, some might improve for lower carbon footprint, some might improve for multiple of those things. And using data in a systematic way, collecting this and giving that insight out of this data to the customers to get to the root causes and to the better decisions faster, this is all what Insights Hub is all about. So it’s data-driven manufacturing for better decision making in your continuous improvement process. And let me maybe give you one example of what this actually means in a little bit more concrete scenario. Just imagine you are a soft drink manufacturing company and you have your filling line and you are the shift manager. You come in in the morning and you look at your overall equipment efficiency, which is one of the major production KPIs to look at how you are doing in production.
It basically measures what you have as performance, what you have as availability in your equipment, and what you have as quality outcome. These are the three elements from OEE, overall equipment effectiveness. And you come in the morning and as a shift manager, you look at your OEE number and you say, “Wow, this is only 75% something must have happened.” So with Insights Hub, we give you that kind of transparency about how your performance is doing and in that case, the shift manager can double click on the OEE and sees, “Oh, there we have actually a performance problem. And the performance problem is with the leak testing machine.” So that’s the machine element and the filling before actually the soft drink is filled in the bottle, there is a machine which puts air pressure into the bottle and see and tests whether the bottle has no leaks, so it’s in perfect quality before the soft drink gets in there.
This is a process that takes typically a few seconds and that leak testing machine was actually the bottleneck and the performance of that machine was 25% lower than it is usually the case. So that’s why that OEE number he looked at in his dashboard was negatively impacted and there was this performance loss of 25%. So what does he do now? He double clicks on the leak testing machine and he sees, because Insights Hub is a IoT driven system, so you can actually go down to the individual piece of equipment, the leak testing machine and in the equipment to the individual components. And in that case he double clicked on the compressor. And the compressor has a KPI, which is pressure because the pressure has to be built up to 25 bars to do the leak testing.
And then the leak testing takes exactly three seconds. And then if the pressure was held, then the quality of that bottle is okay and then you move on and do the same thing with the next bottle. But in that case, he sees on his IoT condition monitoring chart in the Insights Hub monitor, so he clicked in the OEE on the leak testing machine and leak testing machine he went to the Monitor application, which is directly integrated and linked, and he sees that that pressure is not going up to 25 bar for each and every bottle. But for every third or fourth bottle, it only goes up to 23 bar, and then the leak testing takes not three seconds but five seconds because if the pressure is not high enough, it just takes longer to make sure that the bottle really has no leaks. And this effect actually had the impact on the overall machine so that there was a performance loss of 25% and you had way less bottles being tested, which had an impact at the outcome at the end of the line.
So that simple example gives you that insight of now you have an impact on the OEE, you see this when you come in in the morning and then you double click and go down to the root cause with a few mouse clicks. You find out that’s the leak testing machine. And then this actually the compressor in that leak testing machine because of the pressure is not going up to the level which you expect it to be, and that’s why you have the impact. So with a few mouse clicks, you get down to the root cause and now it closes what I said at the beginning, we help customers to make better decisions faster because you know the root cause. Now that shift manager can decide whether he goes directly into maintenance mode and repairs or exchanges that compressor or he waits for the next maintenance window or the next shift handover to actually find time to make this repair, that maintenance.
In that case, he lost 25% of his capacity and therefore he would certainly go directly and fix and repair that compressor or exchange it so that he gets up to a hundred percent of performance again. So just a simple example where you start with Insights Hub and data-driven manufacturing with transparency on your production performance and then it helps you to double click, find the root cause and get better and faster decisions to get back to your expected performance again. So this is all data-driven manufacturing, smart manufacturing, and to be part of that continuous improvement you find on the shop floor everywhere.
Spencer Acain:
I see. It sounds like you’re really taking all this data and making some value out of it. And that of course to me just says that that’s a major AI application right there. So maybe you could expand on how you’re applying artificial intelligence to these problems that you’ve mentioned and the various benefits that you’re getting out of Insights Hub. Surely there’s some AI happening there to let you reach these conclusions, like you said, in just like four mouse clicks to find the problems, then the root causes of issues and whatnot.
Ralf Wagner:
And actually Spencer, that’s a very good point because in the last I would say very few years, maybe two to three years, our solutions are getting more and more AI embedded and empowered because it’s all about the, and the customer don’t care about the technology to be honest. They’re interested in getting to this better decisions to the root cause analysis of the issues they discover on the shop floor faster. That’s where the value is. It’s actually how you can improve according to my KPIs. And technology is an enabler to get there. And as AI is becoming more and more accessible in the last few years, not only from a technology but also a cost perspective, we have continuously improved the usage of AI for our customers in Insights Hub to get to this additional actionable insights and better decision making.
And we cluster those AI enabled solutions in four buckets. So let me briefly go through the four. So the first one is out of the box solutions, the second one is analytical tools. The third one is AI model management execution for the data scientists. And the fourth one which we just added last calendar year is the production co-pilots.
Spencer Acain:
Wow. It sounds like you’ve really got a lot of different AI applications in the works as it were. But I think that’s a topic we’re going to have to save for the next episode because we are about out of time here. So once again, I have been your host, Spencer Acain, joined by Ralf Wagner on the AI Spectrum Podcast. Tune in again next time as I continue my conversation with Ralf and we learn more about those four AI applications.
Siemens Digital Industries Software helps organizations of all sizes digitally transform using software, hardware and services from the Siemens Xcelerator business platform. Siemens’ software and the comprehensive digital twin enable companies to optimize their design, engineering and manufacturing processes to turn today’s ideas into the sustainable products of the future. From chips to entire systems, from product to process, across all industries. Siemens Digital Industries Software – Accelerating transformation.
