Quality assurance · Production

Buderus Edelstahl adopts AI-powered predictive maintenance on DeutschlandGPT, saving over €300k annually

The problem

Over 400 machines at Buderus Edelstahl generate massive volumes of process and log data around the clock, and a single unplanned forge press stoppage can cause five-digit costs per hour. Building a dedicated ML model was ruled out due to the time and investment required during an active transformation, and the highly sensitive machine data could not be processed outside of secure European systems.

Workflow diagram · grounded in source
1
Machine data upload
trigger
“Den entscheidenden Impuls gaben die Abteilungsleiter in der Produktion selbst. Im Rahmen eines Projekts, das von März bis November 2025 lief, begannen sie, Maschinen-Logdaten und Stichpläne in DeutschlandGPT hochzuladen und mithilfe leis…”
2
Maintenance protocol integration
integration
“historische Wartungsprotokolle als zusätzlicher Kontext eingebunden, sodass die Sprachmodelle ihre Analysen auf einer breiten Datenbasis durchführen konnten”
3
Forge tool wear detection
ai_action
“Spezialanwendung für Freiformschmiede: Erkennung von Werkzeugverschleiß anhand von Druckprofilen und Temperaturverläufen”
4
Rolling mill deviation detection
ai_action
“Spezialanwendung für Warmwalzwerk: Identifikation von Abweichungen von definierten Stichplänen”
5
SAP system output
output
“Überführung der Ergebnisse als Ablauf- und Stichpläne in das bestehende SAP-System”
Reported outcome

Around 95% of analysis tasks previously performed by external service providers are now handled by AI-powered specialized applications, with annual savings of over €300,000 in consulting fees.
Unplanned downtime has been reduced as critical wear patterns are detected early, enabling maintenance during planned production breaks rather than emergency scenarios.

Reported metrics
external analysis tasks internalized by AI95%
Annual savings on consulting servicesüber 300.000 Euro
Unplanned downtimeReduzierung ungeplanter Ausfallzeiten
Cost per hour of unplanned forge press stoppagefünfstellige Kosten pro Stunde
Reported stack
DeutschlandGPTOpen Telekom CloudSAP
Source
https://www.deutschlandgpt.de/case-studies/buderus-edelstahl
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Around 95% of analysis tasks previously performed by external service providers are now handled by AI-powered specialized applications, with annual savings of over €300,000 in consulting fees.

What tools did this team use?

DeutschlandGPT, Open Telekom Cloud, SAP.

What results were reported?

external analysis tasks internalized by AI: 95%; Annual savings on consulting services: über 300.000 Euro; Unplanned downtime: Reduzierung ungeplanter Ausfallzeiten; Cost per hour of unplanned forge press stoppage: fünfstellige Kosten pro Stunde (source-reported, not independently verified).

How is this quality assurance AI workflow structured?

Machine data upload → Maintenance protocol integration → Forge tool wear detection → Rolling mill deviation detection → SAP system output.

Related quality assurance cases