Möchtest du unsere Inhalte auf Deutsch sehen?


More efficient shopfloor: OEE and productivity management in extrusion


Click on the button to load the content from Spotify Player.

Load content

Listen to the IoT Use Case Podcast on Spotify.
Listen to the IoT Use Case Podcast on Spotify.
Listen to the IoT Use Case Podcast on other platforms.

IoT Use Case Podcast #106 - ENLYZE + Storopack

In this episode of the IoT Use Case Podcast, host Ing. Madeleine Mickeleit welcomes two guests: Henning Wilms, the co-founder and CEO of ENLYZE GmbH, a software and production automation company, and Benjamin Schlüter, the plant manager of Storopack, a global family business specializing in protective packaging and technical molded parts.

Episode 106 at a glance (and click):

  • [13:11] Challenges, potentials and status quo – This is what the use case looks like in practice
  • [30:24] Solutions, offerings and services – A look at the technologies used

Podcast episode summary

ENLYZE GmbH offers a standardized product solution called “ENLYZE Shop Floor BI” that helps companies make data-driven decisions and optimize their production processes. In this podcast episode, we answer questions like:

– How can data be captured in a scalable way?
– How can a system be programmed to communicate?
– How can data preprocessing and utilization be standardized to determine which product can be manufactured best?

Henning Wilms explains some of the use cases they implement with their customers, including optimizing overall equipment effectiveness (OEE), recording machine downtime, and product traceability. The main goal is to improve process understanding and enable productivity and OEE management.

Benjamin Schlüter gives an insight into Storopack and its production facility in Wildau, where they manufacture bubble film in various models. He emphasizes the importance of tradition and innovation for the company and talks about the challenges they face, especially in relation to the digitalization of their processes. Some of these challenges are the fact that one employee has to operate several plants at the same time, the different skills of the employees and the increased complexity of the production process due to the use of recycled granulate.

The business case is discussed and also how ENLYZE’s solution helps to overcome these challenges. They talk about the importance of real-time data, employee training, quality improvement and problem analysis. ENLYZE emphasizes the ability of its software to collect and preprocess data from various machines and systems, while Storopack highlights the benefits of the solution from a plant manager’s perspective.

Overall, this podcast episode offers a deep dive into the importance of data and digitalization in modern manufacturing and how companies like ENLYZE and Storopack are working together to optimize their processes and get the most value from their data.

Podcast interview

Our guests are Benjamin Schlüter, Plant Manager of Storopack, and Henning Wilms, Co-Founder and CEO of ENLYZE GmbH. Let’s go!

Hello Henning, hello Benjamin. Welcome to the IoT Use Case Podcast. I’m delighted that you’ve taken the time to be here today. With it are reported from the practice. Henning, maybe to you first. How are you doing? And where are you right now?


I am very well. In fact, I just stayed home today, I’m working from home. This has the advantage that there is not quite so much hustle and bustle here. Of course, coffee tastes a bit better at home than in the office. I couldn’t be feeling better today.

Very good. I know that too. We actually have a portafilter machine at home since this year. That is pretty luxurious. It was a birthday gift. I am super happy about it. Your home is in Cologne, right?


Our office is in Cologne, but I live in Düsseldorf.

I’m glad you’re here with us. Benjamin, how are you doing right now and where are you? Are you also working from home?


Yes, thank you. I am also doing great. I just finished two weeks of vacation, which means I’m still refreshed. I am actually sitting in my office today, which is in Wildau, 20 km south of Berlin in beautiful Brandenburg.

Very nice. Where were you on vacation, if you don’t mind me asking? Did you stay in Germany?


I was actually at home. It was my son’s birthday, which means we celebrated two or three birthdays to varying extends.

Yes, that’s always the best, when you have some time with the family at home. Very cool. I would like to start off a bit casually and introduce you. Henning, first to you, ENLYZE. In general, you come from the great industry of software and production automation. You have a standardized product around operating point optimization, so you have a software with a tool, which enables a data-driven decision. “Some of that Lean Management touch and also MES enhancement.” Among other things, you answer questions with your product. How do you get the data in a scalable way? How do I get the data or the facility to talk to me? And how can data preprocessing be carried out in a standardized manner? That’s where you do everything from process data analysis to KPI tracking. I hope I haven’t forgotten anything now, maybe you can add a little from your perspective.


Exactly, I guess that’s going to be explored a little bit more in the course of the podcast and more concretely based on the examples that Benjamin and I brought. But on the whole, it fits quite well.

Very cool. Let’s talk about that first. With which customers do you actually work? I think on the basis of that you always learn a bit from practice how the whole thing works. Do you have a few examples perhaps?


Yes, by and large we are in the industries that have continuous, semi-continuous or batch production processes. Of course, many come from plastic extrusion, which we will also discuss today, but mk Plast would also be an example. They were also our very first customer, a small extrusion company from the Eifel region. It is located right next to our Aachen University, where we started. We also have a biotech company like CO.DON as customer. There’s the use case with you on the homepage, where it’s a lot about process stabilization, process stability, traceability, and quality assurance measures. Storopack is here with us today. The focus is clearly on understanding and increasing productivity. Primarily, all of this where I have continuous processes, role to role, a lot in the packaging industry.

Very cool. I would also like to point out that mk Plast, for example, is also a really exciting project. We have the whole thing online, as you mentioned, on our platform. There you can read everything again and also find the projects of you. You are also represented in our network, which means that you are more than happy to answer questions?



Have you learned a bit from these customers about what use cases you implement there? Can you tell us what use cases your customers are talking about? What are the topics and use cases that you implement?


On the one hand, there is a technical component, but for us that is a means to an end. But there is also a strong diffusion again, from the market, because the bottom line is that today we can handle very, very heterogeneous machine and plant fleets very well and digitalize them. Some of them are from the late 80s and some are brand new. It starts with the plants that have a Siemens control system or that have an Allen-Bradley control system or whatever and that again have a monitoring system from KEYENCE installed in the periphery. Collecting the data of such settings is a solved problem for us today. The data are, of course, only a means to an end. For us, the use cases are clearly about productivity management and OEE management. That starts with KPI tracking, that we build that from the machine data and provide a good understanding of how productive you actually are, to evaluate that on a consistent, comparable, resilient and non-falsifiable, robust basis. Then, building on that, we go into different dimensions. Record downtimes, understand, analyze, derive measures, fallback traceability, process stabilization, machine setting parameters. That’s what you mentioned at the beginning with this operating point optimization, with which machine settings am I actually most productive, what is my <<golden run>> behind it and how can I reproduce it as well as possible. Performance management, improve quality, reduce scrap, and reduce process-related scrap. These are the typical levers.

Benjamin, I’m super happy that you also took the time to share a bit about your company today. You from Storopack are the leading specialist for protective packaging. I think you guys do bubble film, for example, and technical moldings. How did you actually meet each other? Was this through a trade show or was it random? How did that actually come together for you?


The first contact was with Mr. Wilms, or Henning, and my boss, the plant manager at the time. At that time, I was still working as a lean manager here at the site. At some point, my boss and I sat down and made it our goal to push forward the whole issue of digitalization here at the site. Because extrusion is our absolute core process, we were immediately back in contact with Mr. Wilms.  I should get in touch with Henning about that. That’s what we did then. And so we came together pretty quickly.

Henning, you then got back to me and said, let’s go?


Exactly, yes. Benjamin, there was once a press release from you about your new plants. And that was the starting point where we became aware of you, so the circle closes quite nicely. The very first plant we ever established, at mk Plast, was from the same plant manufacturer as the extrusion plants you also have in use. That was, of course, a nice conversation opener for us to kick off with at the time. Then one thing led to another.

Yes, very cool. Let’s dive a bit deeper into this project again. Benjamin, I also find your core business insanely exciting. I had just mentioned it, you are a specialist in protective packaging, a family business operating worldwide, and your goal is to provide your customers with the perfect protective packaging solution and to support them in the long term. Is bubble film the typical thing you guys produce? What do you produce at the location?


Exactly, Storopack basically has two product areas. One is the tailor-made solutions that are also used in the automotive sector and in healthcare. Then there is the other area, flexible product solutions. Among other things, we have paper solutions, the bubble wrap, which we produce exclusively here in Wildau at our site, the corresponding test equipment or end devices, with which the customer can then inflate our bubble film and then pack it into the cartons.

Very nice. So, you mean those small bubble wraps that people like to ‘pop’ for that satisfying feeling, the ones commonly found in packaging, right?


Yes, not quite. So not the usual bubble wrap that you still know as a child, that you just liked. They are on a larger scale. Often, when you order items online, you’ll frequently come across our various bubble wrap products. One is squared, if you want to put it that way. And then there is also what we call the <<engineered>>. They look more like bubbles so to speak, we have the product solution in different molds. That means not only the classic PE film, i.e. with as-new material, but also more strongly, which is absolutely the focus on Storopack, with sustainable solutions. We produce 50 percent recycled film, 100 percent recycled film with biomaterial and also for ESD, which means electrostatic devices or products that are transported. This means that we then have a fairly broad product portfolio that continues to evolve.

A very important point you raise. I was just about to go back to that, I think everybody listening now knows that. Almost everyone has ordered from Amazon at some point. You can roughly imagine what these materials are. It’s a good thing that you’re doing this. I just read a press release from you now as well. You are really pushing that and are also very innovative, also in research. Maybe you can tell us a little bit about your vision for digitalization and which use cases you want to implement.


Yes, very much so. Exactly, if you look at our production today, we have a classic MES system in use. We use SAP and here and there smaller software solutions. But the big approach to digitalization and software that is used there is not yet available on a large scale. We then conducted an analysis and took a look at our internal processes. Where is waste actually found in the process? This starts with the work of our managers, partly administrative activities, reporting, processing real-time information. In order to get to a basis faster, as Henning has already said, to tackle and solve problems, but also the pure production process. How can we work more paperless, have information ready faster and track our performance? So there were several vendors that we just looked at on the market. It’s amazing that there are lots of different solutions available and also lots of users. It’s not easy to have an overview of all the solutions available on the market. We have dealt with different manufacturers and suppliers and informed ourselves. Does that work with our use cases? In terms of performance, we explicitly looked at the production processes and areas. That is, extrusion, as I said, as our core process, pacing process, that was given priority 1. So, of course, we looked at ENLYZE and how we can use their app to support our processes and also our employees, also in connection with the topic of lean management and shopfloor management on a daily basis. ENLYZE has already been able to show us a lot in a demo, which has met our needs. That’s how it developed.

[13:11] Challenges, potentials and status quo – This is what the use case looks like in practice

You have chosen the right expert for the extrusion topic. To give listeners insights from you, can you take us into your process world? What does an extrusion line look like? What are these processes? Based on that, I would then like to talk about waste issues and the challenges that need to be solved.


As I said, we have a two-stage production process. One is blown film extrusion, where we produce the semi-finished goods. In the downstream process, we have what we call configuration. There, the semi-finished product is processed into the finished product, i.e. provided with a perforation. There is a certain welding pattern, which results in the bubble cushion shape. The whole thing is then checked and made ready for shipping. If you go back to extrusion, you have to imagine that we process granules on a large scale. And that means this granulate is added to the extrusion line via feeders. Then it’s mixed, much like cooking, I’d say. You need a certain percentage of one material and a certain percentage of another material. The whole thing is then mixed together, extruded, that is, it goes into an extruder screw, then it is melted, and then it results in this bubble and therefore blown film extrusion on the line. In the end, the bubble is made to lay flat at the top, if you will, which means this tube is basically already folded into such a film for the first time and then printed or rolled up. This is actually the semi-finished product, which we then temporarily store or further process.

What you just mentioned with the welding, that is then the separation of the individual bubbles from each other, so to speak, what you do there?


Exactly, so the product is not yet inflated here in the house. The film is basically as you know it and this welding then just gives the format. That is, about it gives the shape of the final product. When the customer then blows up the product at the end via our equipment, which he then needs for this, then the perforation virtually tears off and the welding ensures that the air remains inside the cushion.


These are also two different processes. The bubble that is in the blown film extrusion. Benjamin correct me if I’m wrong, the bubble is certainly three, four, five meters wide in diameter and it is then crushed in the configuration, cut on the winder and then perforated and welded as Benjamin has just told us, these are two different downstream processes that then result in a final product at the end.

Okay, I think I’ll just have to stop by your place and take a look. I would love to see that mega.


Yes, one is always mistaken. You think it’s such a simple product in the end, but if you look at the process for manufacturing, in extrusion, it’s extremely complex. So just the extrusion. Exactly, and that’s just something super exciting.

So exactly, you are of course the experts and these are then very process-specific expertise that your employees bring to the table. You’ve just mentioned it, it’s now also about reducing waste. Maybe we can talk a little bit about your business case. In the end, you want to save time and money. Can we talk a little bit about challenges that you have seen in everyday life


Yes, very much so. Of course, it starts with relatively clear, simple things that even an outsider can see pretty quickly in our case. We already have a challenge due to construction, i.e. we have an old building, an old hall and there was an extension to it. And it was decided, also for safety reasons, to mirror the halls. When you are here on site, at one end of our hall you will find the old extrusion hall with four lines and at the other end you will find the new extrusion hall with two new XL lines and in between there are a few hundred meters separating these two areas. Even in terms of work organization and team scheduling, it is a challenge here and there for the employees to see how things are going in the other hall. We have a team lead that oversees these two halls and staff and he has to shuttle between these two halls if there is a need for support or intervention here and there. That’s where we have the first issue, which is that there are of course also operating terminals at the plant, where you can see all the parameters and dive in, but they are not so transparent and visually displayed that we can say that he always has an overview of how things are going in the other hall. So a lot of walking.

The second issue related to this is that we also have multi-machine operation by one employee. This means that one or two employees operate two to three, sometimes even four systems simultaneously. That also depends here and there on the staffing level and the workload. But it’s not the case that an employee operates a system from front to back in the classic way; instead, there are a wide variety of tasks that have to be covered in everyday life, such as cleaning, quality inspection, problem handling, setup, and so on. This means that one line on the left can be running smoothly and quietly, while on the right you have a problem and still need to know how stable the other line is.

Yes, that’s probably also a big issue for new employees coming in who need to be trained. You have to know the plants first, each one runs a bit differently and so on. I also imagine this to be very challenging in terms of the competence structure.


Exactly, absolutely important point. This is also where Henning and ENLYZE directly said they have experience from other customers. I think you are recording 7000 parameters, Henning. And so you also have to imagine what the employee could set on the extruder. Of course, ENLYZE helps us to process this in such a way that we say, look, the certain parameters are interesting and absolutely relevant for you. If you are perhaps not yet at that level, then the team lead comes in and can dive into a completely different database.


After all, this is a truly organ-overarching theme. In the case of extrusion, I believe quite extremely, because the plant is simply really very complex. We have the most experienced employees and the slightly younger employees who may not have been there as long, and then I have so many influencers. What is the outside temperature, what is the humidity, what material is ready? Especially with recycling, it becomes even more complex and I have to somehow stabilize this process with these countless parameters. Depending on how experienced I am as an employee, the better I get at it. By recording the data and ultimately comparing it with the history, we can then filter out what has historically worked particularly well for certain products under certain conditions. This is then ultimately fed back to the plants, so that in the end every machine operator can become the best machine operator and build accordingly on the collective experience of his colleagues. That’s definitely one of those topics where we keep going in, which is also quite noticeable at Storopack, but also very much proven. It was implemented to squeeze out a few percent and just give everyone guidance and help.

I think it’s an important point to execute data-driven things and tasks. This does not mean that the employee is really the expert. The person simply knows his or her way around very well. Now it’s just that of course you also get a recommendation based on data or simply have a transparency that you didn’t have before and simply also save time and can do other things in the time. So I think that’s also very important, that something like this doesn’t replace anything, but it’s simply a data-based tool that you can work with, which is simply an enormous relief in the job.


Absolutely. And that’s where the most important two challenges that we’ve seen where ENLYZE supports come in. We produce 24/7, 365 days a year. In connection with our lean management, i.e. our daily management, we also have a staggered structure with a communication cascade. Occasional incidents have occurred within this structure, some of which the employees cannot be blamed for. As mentioned earlier, they operate multiple machines and may be busy at another plant. This means that changes can occur in the product, raw material or plant that require immediate intervention. However, it is not always possible to check all parameters directly. Where does ENLYZE help us here at this point? What both of you have just said, the data situation is much clearer, or I can simply go back into history and look at when something happened in the process or in production. Now was this a one-off event, which was there for maybe 10-15 minutes and kind of had a brief impact, or are we seeing a trend? We can also set up the problem analysis in a completely different way, now and then, you can’t reproach our employees for that, maybe it wasn’t the expert at the plant at that moment. The just acted according to experience and best knowledge, but then see possibly an analysis that the problem was more complex. Especially on the night shift, where we don’t have the full support, for example from the management here and there, you could see that we lacked the basis in terms of data and data analysis, or the time component.

I can imagine. It’s sometimes external or in the upstream and downstream process any challenges that may have never been encountered before. Or you have changed the supplier, who suddenly supplies different additives that are used there. These can be such a wide variety of influences that you can’t even foresee yet, can you?


Totally correct. And that’s basically the very biggest point now where we say that’s the Challenges that also still accompanies us. When I started, in 2019, we just started manufacturing on a large scale with recycled products, so using recycled raw materials more. That is, before you can still imagine it like this. The goods arrived in the silo. This was, as I said, mostly new goods, very homogeneous in terms of quality, processing parameters, etc. So I was able to adjust the plant and, to put it bluntly, drive through a week without any major issues. With the whole issue of recycling, it’s now a completely different story that has become much more complex. Suppliers can now no longer deliver the goods homogeneously on a large scale, but it happens, and this is almost inevitable, that here and there material is either contaminated or polluted and not every container has the same property as the other. This means that we still have certain mechanisms upstream internally that take effect, but when a system is nevertheless processed, there are still hole cases here and there. That is, there was a particle in the material that causes the hose to have a hole. In the worst case, the system can break off, that is, the film can break off and the system can crash. So you have to start over again. And so that means with this processing of recycled material, it has become much more complex. We have to pay attention to pressures, temperatures, performance in terms of speed, torque, etc., and this was not so much in view before, or even necessary. That’s where ENLYZE is again quite crucial, that we can’t just look at plant specifically. The greatest added value now lies in the fact that we can say we know which material should run with which performance and how. Keyword Golden Run. And we can also compare this over a time history and then see if anything has changed in the material. That gives us completely different options in the meantime.

Mega, yes. So, to summarize your business case again, it’s about empowering employees to analyze problems, to expand the expertise that they already have, to save time, and to increase quality. The example with the hole case, if a hose has a hole, this can of course lead to a loss of quality or even the whole batch has to be thrown away. Problem analyses and also using this historical data or perhaps other data, I would ask a very brief question again. The data issue is. insanely exciting at the point. Can you give some examples like that? Just a few simple examples from the field, from your plant.


As I said, the biggest issue is that I still have to go to the plant today. So I need to get to the terminal, there to search the history. In some cases, data is also gone after about a week. That is, they are not stored in the long term. Nowadays, I can look at a time series, go into ENLYZE, either pick the job that’s currently running, or compare that to a job that ran two, three months ago, and then I can overlay the parameters, for example. That means I’m looking at mass printing, among other things. So how did the material behave in the extruder? Has the increase in mass risen sharply? This then leads in the end to the fact that we have to switch off the plant more often, clean a sieve and then start again. We can also work much more transparently with this and say how effectively the material is working at the moment and how good our OEE is in relation to the material, i.e. to the actual order and no longer just to the plant. For example, this is a very specific case. There is also, which is also super nice, the possibility to tell the ENLYZE how the parameters must be set? Is there also a very specific case, what may not be switched on? We have a keyword here, the grooved bush. This is switched on for a particular product and should not be switched on for other products. This means that we can preventively avoid mistakes there as well.

What is and will be the biggest focus now is processing real-time information. With Henning and his team, we are now working on dashboards. This is also valuable for a manager who goes in there and doesn’t crawl into the depths of these terminals every day to fish out plant-specific parameters. That is, you see and this comes from lean management this famous 3-second rule, meaning I see in 3 seconds, is the process stable or not? ENLYZE helps again in terms of how we will switch televisions or monitors in the hall, which again show our most important parameters at a glance and we then know exactly at any time we are on green or we are just in the yellow-red area.


I think what you’re involved in, Benjamin, is such a classic customer journey that’s emerging in this digitization sphere. In that first step, where we capture and collect the data and then we first learn from history, what works well, what doesn’t work well, and then use that learned knowledge. With you guys, it’s a little more difficult in complexity with all the recycled material. To think about the future, what can we pack into such a monitoring system from these empirical values, for example, that is always dependent on the current production context, i.e. which material is just finished, which products are just finished, on which systems is monitoring provided, which simply helps all workers, machine operators, shift supervisors and managers to maintain an overview of production.  Then accordingly from this learned, from the history to deduce what kind of mistakes I can avoid this time. This is definitely one of the journeys that many of our customers go through, and it’s always exciting to see, accompany, and observe, because many discussions then develop around it, new use cases emerge, new ideas are developed, and the impact that you can measure at the end of it is really there.

[30:24] Solutions, offerings and services – A look at the technologies used

Each case is a little different. If you listen and say, we have that as well or something like that, then you can enter into the discussion with Henning and Benjamin. But I would go in on your case, how did you do it exactly? How do you get the data, what we said at the beginning? How do you get the plant to talk to you? How then does this evaluation work, especially in a standardized way? We just had a couple of data points like that now that we talked about. For example, melt pressure. This is one such data point. Henning, if I want to get at this data now, will you bring the hardware? How does that work? So how do you get this data?


What is important to us is that we develop everything completely from a single source. That means we don’t now have different suppliers and technology components that we plug together. We really started using our own edge device to develop the drivers to deal with just these heterogeneous assets in a practical way. This gives us control to adapt things and develop them further. At some point, an update is applied and we know exactly where we have to adjust which drivers. So today, with this edge device, we can actually connect every common machine type, as mentioned at the beginning, every common automation manufacturer, whether it’s Siemens or Mitsubishi or whatever, we can get all of that connected first. This data is then pre-processed a bit on the edge device before it is finally streamed into the cloud and enriched with further data from an MES system, perhaps including quality data. From that, we ultimately build the tools and the analytics that Benjamin and his team can then use in the end.

Above all, you do this relatively quickly. I know this from other projects of yours as well. I think you can see the first data from such a system in less than 24 hours, right?


Exactly. It is simply because everything is preconfigured. We have developed everything in-house once completely from the edge device to the corresponding dashboards. The bottom line is that when we go to the customer, everything is ready. In the end, we only have to do the engineering and configuration once more so that the edge device talks to the plant at the end, and then we’re done with it. The rest then runs in the cloud environment, in our system, in collaboration with the customers, the configuration, the customization and so on and so forth. But basically it’s just done very, very quickly.

Yeah, cool. How does the data processing then work in the next step? Benjamin, you had said that, you guys are using an existing MES system, also an SAP, you can integrate data that way, but also take those data types from the OT side. Henning, how does that then feed into your cloud architecture or on-premise architecture accordingly?


For the analyses at the end, it is of course important to understand this production context. For us, this means that we synchronize out of the MES in this case what the current production order is, so that you have the traceability. But also which article is currently being produced, i.e. which material number is currently being produced on the line, so that we have that as a basic building block. Here and there there is additional information that we extract, but then we ultimately use the interfaces or the database architectures that already exist from the other systems and then synchronize the data with us via these interfaces. We then marry them in the cloud in such a way that meaningful analyses and derivations are possible at the end.

For many, the topic of the cloud sets off alarm bells. Benjamin, you also host a lot of data on site and then a selected part that is necessary for this analysis probably goes to ENLYZE, right?


Yes, but I can confirm that, it was an issue with us as well. That wasn’t a foregone conclusion. Of course, there were also consultations and discussions with IT. I think if it hadn’t been for us as Storopack, ENLYZE would have been through here in an hour and a half and hooked everything up and we’d be ready to go. In record time. But IT will of course take another look here and there.

I don’t even want to open that chapter now, because I think there are a lot of things to consider. There are also separate episodes that I’ve done on that, because it’s very important that IT looks at that and has things on the screen. But I think that’s where I’m going to make a… (cut).


I think the most important thing is just to understand that all the concerns are absolutely valid from our point of view. But in the meantime we have been hearing it again and again in the same way for five years. There are also good arguments, techniques and tools to address these concerns and then also to invalidate them. We are happy to go into the discussion and present what we have now thought about for the typical concerns and then rebut them accordingly. Then there is usually also a way, there was at Storopack now yes. It is part of talking about it and after that it is good in itself.

Yes, there are also some clever solutions for architecture, what you can do there, but that is perhaps too far for today. What would interest me again now would be the evaluation. We had said there is also a standardized evaluation that you can do. I think Benjamin, you also mentioned your production planning or also your management. They also get a dashboard. You had talked about 7000 parameters. So how does this analysis and evaluation work for you in the end? What does it look like?


The beauty is that the ENLYZE app allows us to make it all user-based. This means that the production manager can look at the data differently than our production support, which provides strong support for extrusion, including in the area of development. The quality manager can look at it again with other parameters from his glasses. In the end, this results in completely different possibilities as we have today. That means from those 7,000 parameters that might be there, we can build that for each individual user as well as the line staff in a way that is basically most effective and valuable for them to work with the data. As I said, I can build up the whole topic multi-dimensionally by saying that the employee sees the most important parameters for him in his app, as it is designed for him. Then we also have the link with these dashboards in the production areas, so that I can say that the most important parameters are visible at a glance at any time in real time, so that I also have a completely different application there.

So that means for your works for example this topic, I can see the historical data and know the screen could be cleaned. I think you had the example earlier that so historical data that your employees, female employees on the lines there are probably interested in.


Exactly, they can do that today, but they always have to go to the terminal and then get in there. But what we want now is this 3-second rule. I can see at any time in real time how my plant is performing in relation to our most important parameters. I may be able to intervene earlier than I do these days? I have to go there first, or the alarm has to come first, when I could see through ENLYZE before, or ENLYZE gives me a hint, watch out, something is happening here.


Exactly, I think that what Benjamin is also just describing with this is also something for us that we like to observe from the outside. <<The company’s mission is democratized manufacturing data>>. So our goal is that every process expert – the process expert can be a process engineer, but can of course also be the machine operator or a shift supervisor or a production manager – finds a level at which he or she ultimately uses his or her process and expertise to develop a solution that is right for his or her needs. The topic of the cloud could also be briefly addressed again here, as we at ENLYZE are active in this context and are initially setting up the technological infrastructure. Ultimately, we empower our customers and experts to analyze their specific use cases and biggest sources of loss. They can think about how to prevent these losses, what steps are needed to do so, and how to extract the necessary information from the data.

The bottom line is that with the infrastructure we have developed, we then embark on this journey with the customers, where perhaps we didn’t even have mass pressure on our radar screen at the beginning. And now we are slowly learning, man, mass pressure is a big issue. This is adjusted within minutes, suddenly I have the mass pressure with it and can then also build a monitoring dashboard in a few clicks. The beauty in that context is simply that we take all of that IT complexity, all of that technology complexity, all of that IT/OT engineering and so forth away from the customer and allow them to focus all of their knowledge and all of their resources on the business impact and value from that data. As an example, rather than somehow packing three people into his IT department to manage an IT/OT stack somewhere, hire two more Data Scientists. As a rule, this does not yet create any added value for day-to-day business. When you’re at a point where you’re ready and you’re coming up with your own solutions that you can develop now, the bottom line is we’re more of an enabler and train you 1-2 times. Then you can let it run on its own. That’s always fun to watch from the outside, too.


The other day, when you were here, we had the idea of taking another look at the topic of energy management and how we can use the possibilities you have for collecting data for interesting applications that we don’t even have on our screens today.

That is a very important point that you have just elaborated. I think that’s where IoT comes in, when I can use data across the board. We had given this example with recycling, that is, with hole cutting. For example, when does the hose have a hole? That’s a nice business case that’s relatively clear. Viewing data from which supplier the batch comes from or integrating other trades is not possible with a classic MES today. That’s where it stops, and that’s where you need these cross-data-pool solutions, where use cases come into play that Benjamin mentioned. I also know of many other cases, now it’s about CO2 tracking, where I have to spend a CO2 footprint per product, for example. That’s probably an issue with you guys, too. So I can only do those things with it and I have the scalability in the cloud. One more question, since I know there are some techies listening. Henning, many already work with Grafana or Node-RED. Can you do that too?


There are already many, many cool tools that, with a little training, allow Benjamin and his team to easily build their own dashboards. That can

For some, it can be for reporting in Power BI or whatever the other tools are called. For others, it can be monitoring in Grafana or Node-RED or something else. Of course, we have our own ENLYZE app that takes care of all this OE management and where we always start with the customers in the first place. But at some point we grow beyond this app. Then there’s the one use case where we learned, we have so much downtime. To solve that, we learned historically that certain parameters need to be monitored better. Then, of course, in Grafana you have a playground where through our integration, which provides the data, then Storopack can just build itself a solution in that case to get rid of the problem. This creates a high agility, a high speed of implementation and problems are solved quickly. Our intention in this context is to avoid Benjamin saying, “That would be great if we had that,” after acquiring a new piece of knowledge.” This is followed by discussions, project planning, formulating specifications, and clarifying requirements. In this process, misunderstandings could occur, resulting in a delay of several months. However, our goal is to enable rapid implementation through seamless integration with Grafana. We want to empower the process expert to focus his attention on designing the dashboard himself as needed. We want to avoid him having to explain what he wants, to avoid misunderstandings. The end result should correspond to what is actually desired.

Benjamin, one more quick question in the direction of your customers. In the future, for example, you can simply give your customer the option of accessing such data on the basis of this data. For example, what is the CO2 footprint for this product batch? Can’t you also give those insights, that golden run, that kind of data, back to your customers? Doesn’t that make him totally excited when you guys go along with something like that?


That and, above all, completely new possibilities. So as you said at the beginning, foil and plastic is all the more eyed these days. If we can show that we can improve and make that transparent, then that is absolutely something very important for us.

Exactly, so you stay competitive in the long run and your customer is satisfied and you go with the trends. With the solution you have all possibilities. Thank you very much for these exciting insights. A really strong project. First of all, I have to compliment you because it’s very rare that we can talk about things in such a concrete and really process-intensive way. This is really a great added value. I think that almost all cases have a concrete euro written behind them. That was really a really exciting project. Thank you very much for this. Thank you Benjamin and Henning for your time and for speaking so openly. With that, I would turn the final word over to you. Thank you so much for being part of it.


Thank you very much from my side as well. Thanks to you, too, Benjamin. Maybe we’ll meet in six months and see where we are then and what we’ve learned.


You are cordially invited. Let’s see how far we’ve come in the next six months. I thank you very much for the opportunity and for the invitation.

Very nice, you’re welcome and let’s talk on the phone, I’ll come by. I would be mega happy to have a look at it in detail on site. Many thanks to you and I wish you a nice rest of the week. Take care.

Please do not hesitate to contact me if you have any questions.

Questions? Contact Madeleine Mickeleit

Ing. Madeleine Mickeleit

Host & General Manager
IoT Use Case Podcast