Case Study: Zeppelin achieves predictive maintenance and reduced equipment downtime with Splunk

Zeppelin Takes Predictive Maintenance to New Heights With Splunk

Zeppelin is a German engineering and services group known for construction, mining, agricultural and rental machinery and for developing digital business models for the construction sector. Facing a complex, group-wide IT estate (SAP, VMware, hyperconverged storage and thousands of IoT-enabled rental machines), Zeppelin lacked centralized visibility and relied on bespoke scripts and an aging monitoring tool, which limited its ability to monitor equipment remotely and predict failures.

Zeppelin deployed Splunk Enterprise (with DB Connect and the Machine Learning Toolkit) to aggregate and analyze thousands of logs and sensor streams in real time. The solution delivered millisecond-level visibility, enabled an anomaly-detection model to predict spark-plug failures and dispatch technicians before shutdowns, and supported new IoT and business-intelligence use cases showcased at trade events. Results included richer IT monitoring, reduced customer downtime through predictive maintenance, improved system performance and better customer satisfaction.

Zeppelin

Andreas Zientek

Systems Engineer