Spicing Up Innovation: Predictive Maintenance at Kotanyi

Trend Detection Podcast ·

Show notes

Welcome to the Trend Detection podcast, brought to you by Senseye Predictive Maintenance – which gives you visibility and insights into all your assets, from single machines to full plants to help you reduce downtime, increase knowledge sharing and accelerate digital transformation across your organization.

This covers:

Why long-standing manufacturers like Kotányi are embracing digital transformation—and what it takes to turn tradition into innovation with predictive maintenance.

How starting with a single bottleneck machine helped Kotányi reduce downtime, prove value fast, and lay the foundation for future AI-driven improvements.

Why success isn’t just about installing new tech—but about aligning with business goals, involving shopfloor teams, and making insights actionable.

The critical importance of choosing the right partner—offering end-to-end solutions, domain expertise, and a collaborative approach that fits existing operations.

Lessons learned from the frontlines: Avoiding change management pitfalls, breaking down silos, and scaling predictive maintenance with strategy, simplicity, and speed.

You can find out more about how Senseye Predictive Maintenance can reduce unplanned downtime and contribute towards improved sustainability within your manufacturing plants, by visiting: www.siemens.com/senseye-predictive-maintenance

Transcript

Welcome to Trend Detection podcast powered by Siemens. I'm Xenia, your host, and today we are diving into innovation in the food industry, specifically around predictive maintenance. And we are going to explore how this technology is transforming operations in sectors like food and beverage, manufacturing, and beyond. And to help us unpack this topic, I'm joined by Thomas, who will walk us through a fascinating customer success story, with Cottony. A well-known spice manufacturer that's been leading the way in digital transformation. Thomas, it's great to have you on the podcast. Thank you. I'm, I'm very happy to be here. But this is the first time for me to be part of a podcast, and I'm very excited. So before we dive into the details, could you briefly introduce yourself and your role at Siemens? Of course. My name is Thomas and um I'm a sales manager at Siemens. Um, in my job, um, I have industrial companies in Austria with the digital transformation through using uh innovative technologies to make the processes smarter, more efficient, and also more resilient. My field of expertise is predictive maintenance, and it's really my passion to create real customer weather with predictive maintenance. And I had the pleasure of successfully implementing predictive maintenance for our customer colony and, and I would like to share the success story in this podcast. Thank you, Thomas. It's really great to have you here. So maybe let's jump in. Can you start by introducing the customer and what made this particular project stand out for you? Absolutely. Colony is based in Austria and is a traditional brand with over 140 years of history. They produce premium herbs and spices and supply them to over 30 countries worldwide. What is special about this project was the openness and, and also the positive attitude to trying something new. You could practically feel the pioneering spirit right from the start. The desire to become better and faster with harness the potential of, of starter and also to take on a a pioneering role in the digitalization was immediately appearing. And Calvinists also pursuing a digitalization strategy. Couple with the right leadership to implement it and, and these qualities are, I believe are very good breeding ground for, for the successful implementation of innovative solutions. Wow, that sounds really impressive. A 140 year old brand and still pushing the envelope on innovation. That is not something you can see every day. And I think it really shows how even long-established companies can benefit from embracing digitalization. But let's zoom in a bit. Why was predictive maintenance such a priority for Cotai? That's a great question, but let me explain this, just a little bit. Business at Cotton is going very well, and as a result, uh, production requires um a higher plant utilization. This in turn requires also a high plant availability from the maintenance department, and there is indeed room for improvement because colony operates bottleneck machines. Can you explain to me what a bottleneck machine is? In short, a bottleneck machine is the most capacity limited machine in a, in a production line or process. It determines the maximum speed at which the entire system can operate. That means any malfunction or a delay in a bottleneck machine has a direct impact on production. And that must be avoided at all costs. Unfortunately, one bottleneck machine at Cottonni is repeatedly affected by amble on them. And predictive maintenance is of course an optimal level and also starting point for increasing the plant availability. And by adopting predictive maintenance, colony could move from that, from reactive to proactive maintenance. Anticipating problems before they occur and make all the better use of their resources. That actually makes a lot of sense. When operations depend so heavily on uptime, even smaller issues can create big ripple effects. So once Kotay has identified that predictive maintenance could help, what made them choose Siemens as their partner for this journey? They were looking for a partner who could offer an end to end solution, hardware, software, analytics and and services, and Siemens was able to deliver on all those fronts. We had the right combination of domain knowledge, scalable technology, and a very strong local preset. And importantly, we, we work closely with that team to, to ensure that the solution fits seamlessly into their existing infrastructure processes. It, it was very much a collaborative effort. It definitely sounds like a strong match in terms of both technical fit and a shared vision, and I'm really curious now, what did the actual solution look like? As I, as I Ro mentioned, we, we started with the transport system, which is a bottleneck machine, and the goal of the exercise was to, to equip this bottleneck machine, metaphorically speaking, with a high beam, so that obstacles and dangers can be detected in the dark early on. The solution approach is on the one hand, the expanded use of the new frequency converters as actors, and, and that's the central point, as advanced sensors. And on the other hand, an AI-based drive data analytics. All right, I think I understand the solution approach now, but how did Siemens help Cotai bring this whole plan to life? In the first step. We replaced the 20 year old fragravers with new ones. In this step, the communication to the existing Martin Pery was also changed from probables to provenance. In the second step, a virtual industrial PC was installed in, in coordinate IT environment. So the central drive data are transformed from the new frequency converter to the software application drive data analyzer, which runs on the virtual industrial PC. And based on AI algorithm, the mechanical drivesframe, motor, and frequency converter are analyzed separately. It's like a high beam that the operator gets a better view from the condition of the transport system with the help of animal detection. In the final step, data transfer is established between a Wilder Industrial PC and an ESQL database. The maintenance department uses, uses the data from the schoolOI database um for their alarming and monitoring workflows. And with our solution, the maintenance workflows are enhanced with insights from AI based machine data analytics. It sounds like a very well rounded setup. We are not just plugging in new tech, but really connecting the dots between machines, data, and decision making, and I guess that's where the magic happens, right? So now that the system's been running, what kind of results have Cottony seen so far? The results were really encouraging. Within 6 months, they prevented 3 unplanned downtimes and saved around €30,000. They also improved their energy efficiency by identifying abnormal consumption consumption patterns and optimizing drive settings. And upgrading to ProveN gave them faster and more reliable diagnostic, which made daily operations more efficient and reduced troubleshooting time. And from a strategic perspective, it helped advance the broader digitalization and sustainability goals. Wow, those are some impressive numbers, and I can imagine the team at Kotai is feeling the difference every single day. So what is next on their digital roadmap? Looking ahead, we, we are focusing on 3 main areas. First, strengthening IT a the integration by connecting more machines to the Siemens Industrial Edge platform. Second, boosting sustainability through more data-driven monitoring of energy and water consumption. And 3, expanding predictive maintenance across additional machines to catch issues early on. And together, these 3 steps will help Carton stay competitive and future ready. Exciting times ahead for sure, and it's really great to hear how digitalization isn't just about technology, it's also about long-term thinking and doing things smarter and more sustainably. So Thomas, before we close, do you have any advice for companies listening who might be at the beginning of their own digital transformation journey? That's, that's a good question. I have already gained a lot of experience with my AI project. And to be honest, I made some mistakes in the first few projects. But that's just how it is when you enter a new and unfamiliar environment. But I learned from my mistakes and subsequent reflections, therefore, very important to draw insights from, from the mistakes and avoid making the same mistakes again. The first mistake is when you have no change management plan. For example, shop for workers resist systems they don't understand. It's not intelligent when shopful workers are involved in the innovation process. 2nd mistake. Difficult implementation due to complexity. One reason is sealed implementation. For example, when the IT department decides something without improving the shop flow or vice versa. Another reason is choosing unexperienced project staff that missed the bigger picture. Third mistake, automating without rethinking by implementing technology in the hope that we will magically fix broken workflows. But here's the truth, technology is an equal transformation. I totally agree with you here. Reflection on mistakes is a very good starting point, but once you reflected on them, which recommendations can be derived from your mistakes? The most important for us insight is define a clear strategy. You have to answer the question, what do you want to achieve through technology? From a technical perspective, would you modernize an old and outdated system to a current technology? Or would you optimize your processes to become more efficient or effective? Or would you transform the business model as a whole? With all the clear strategy, it's really hard to set the right course. Second answer is you need leadership support and culture. Digital transformation starts at the top, but it needs everyone on board, and leaders must create a framework that fosters innovation. This framework should regulate leadership alignment, protective resources, budget and culture. And when you lack the support from leadership, it is almost impossible to execute change management. Third insight, engage people in the innovation process. A higher rate of participation of the shop workers would be a good indicator of innovation. Implementing technology is not the difficult part. Engaging people in the long-term is the most difficult part. You must align this with your strategy. 4th insight, redesign first and automate later. Don't let technology have distract from the fundamentalist. Process that should lead and technology should follow. Don't just digitize. Rethink how things could work better. 5th insight, stay agile, start small, learn fast, and adapt. Pilot projects are a great way to test ideas without overhauling everything at once. And finally, bring in external partners. You don't have to do it all alone. Consultants and technology providers can bring fresh ideas and valuable expertise. Wow, that's lots of valuable insights packed into just a few points. It's like a mini playbook for other companies. Super practical and something many can learn from. Thank you so much, Thomas, for sharing that with us. It was a pleasure for me. Thank you very much for your invitation and this great conversation. And to our listeners, if you're thinking about how digital transformation can support your business goals, we would love to hear from you. Siemens has the tools, technology, and expertise to help make your operations more future-ready. Thanks for tuning in to the trend detection podcast. Until next time, stay innovative. Please like and subscribe on all major podcast channels and find out more about Sensei predictive maintenance at Siemens.com.

Full transcript (WebVTT)