Vendor-Lock-In is real. But building your SME's industrial IoT platform from scratch may put you into a far worse position. Read this article, if you learn about three fundamental questions you should consider in your evaluation process.

In einer Industrie-4.0-Architektur fungiert ein Historian wie das Langzeitgedächtnis der Produktion. Auf welche Arten kann ich einen Historian realisieren? Was spricht für spezialisierte Lösungen und wann machen Open Source Lösungen als Bausteine Sinn? Unser Blogeintrag versucht für dich den Historian etwas greifbarer zu machen, auch wenn du vielleicht noch nie davon gehört hast...

How do you bring data-driven industrialization projects into everyday operations successfully? In the steel industry, this journey is met with many challenges—from seamlessly integrating diverse data sources and automating complex processes to ensuring the highest levels of data security. Together with RHI Magnesita, we tackled these issues while developing the Health Check Platform. Read on to uncover the insights and solutions we developed along the way.

Manual inspections and the early replacement of critical components are standard practice in many steel plants—but they come at a cost, both in time and resources. Together with Alpamayo, RHI Magnesita has developed the Health-Check Platform, empowering steel plants with proactive, data-driven maintenance solutions. In our joint article published in fmpro Service, we provide insights into our collaboration and reveal how we overcame typical challenges from an OEM’s perspective.

Foundation models like TimeGPT have generated a lot of excitement, with the potential to revolutionize how we handle industrial time series data. Imagine building a model that can seamlessly transfer insights across different assets and detect rare failures based on patterns observed elsewhere. But does TimeGPT live up to the hype? In our latest post, we share the results of our hands-on experiment with real industrial data—highlighting the current limitations, challenges, and why we're still a few steps away from this AI dream.

Imagine starting your day without your morning coffee because your machine failed. Now, imagine the stakes are much higher—like 180 tons of molten steel spilling onto a factory floor. Machine failures in industry can lead to catastrophic consequences, but predictive, data-driven maintenance can prevent them. In this post, we introduce our DeepFMEA framework, an approach that simplifies the development of diagnostic tools, making predictive maintenance way more effective by bridging the gap between data and process expertise. Read on to learn more and download our DeepFMEA Paper for in-depth insights.

You’ve invested in AI, hired data scientists, and seen “promising results” in pilot projects. But you're still missing the impact on your operations? In this blog post, we dive into the often-overlooked challenges of scaling AI from concept to industrial-grade deployment. Discover why static AI models fall short in dynamic production environments and how MLOps can transform your AI initiatives into reliable, adaptive solutions that create real value. Ready to take your AI strategy to the next level? Then dive in to learn more.

The integration of AI into condition monitoring holds immense potential. However, the true value is unlocked only when engineers merge their deep expertise with AI’s capabilities. It is the synergy that forms the foundation for genuinely effective and predictive monitoring. Read on to find out how you can effectively combine the two for optimal condition monitoring.

It’s no secret that Predictive Maintenance (PdM) offers significant advantages for machine operators. However, the immense potential that Predictive Maintenance holds for original equipment manufacturers (OEMs) often goes unnoticed. By integrating PdM systems, OEMs can unlock opportunities that go far beyond mere cost reduction, opening doors to new value creation and service models. Discover what these opportunities are and why manufacturers should think about Predictive Maintenance now.

Die intelligente Produktionsmaschine ist in Großunternehmen längst Realität. Wie steht es jedoch um den Einsatz von Manufacturing Prognostics im Mittelstand? In diesem Blogbeitrag beleuchten wir die Herausforderungen und die Chancen, die datengetriebene Fertigungslösungen für den Mittelstand bieten. Hier erfahren Sie, wie kleine und mittlere Unternehmen trotz begrenzter Ressourcen in der digitalen Transformation erfolgreich mithalten können.

Curious why predictive maintenance initiatives often fall short? In this blog post, we explore the five most common pitfalls machine manufacturers face and offer practical tips to help you navigate these challenges. From misaligned strategies to unrealistic expectations, this overview provides a concise guide to avoiding the mistakes that can hinder your success. Read on to ensure your predictive maintenance efforts stay on track and deliver the desired results.