Predictive Maintenance

Data analysis directly at the machine

Data analysis directly at the machine

The industrial use of machine data is a key driver for greater efficiency, reduced downtime, and more sustainable production. However, in practice, adopting condition monitoring and predictive maintenance often falters due to complex IT structures, high implementation costs, and a lack of data transparency. Igus offers a solution with its new i.Cee² module: this edge module allows companies to quickly and easily capture, visualize, and analyze machine data.

Against the backdrop of rising energy prices and increasing demands for sustainability and resource efficiency, the use of machine data is becoming increasingly important. Only by understanding and specifically analyzing their processes can companies optimize energy consumption, reduce downtime, and remain competitive in the long term. At the same time, many companies feel uncertain about complex digitalization strategies. This is precisely where the Igus i.Cee² module comes in.

This compact, industrial-grade device is installed directly in the control cabinet and operates as an edge device on the machine, acting as a universal data logger and analysis module. Integrated analog and digital interfaces allow for the connection of a wide range of sensors—for example, to monitor current profiles, temperatures, humidity, or forces. Data is stored, processed, and visualized directly on the device. This gives users immediate insight into the condition of their equipment without the need to first set up complex IT infrastructures.

"Predictive maintenance doesn't start with complex systems; it starts with the initial data. That’s why, with the i.Cee², we deliberately focus on data logging as a starting point. Customers begin by capturing machine data, gradually identifying patterns and conditions. This creates a pragmatic transition to condition monitoring," explains Richard Habering, Head of the smart plastics division at Igus. Only in a subsequent step do forecasts and concrete maintenance recommendations—the hallmarks of predictive maintenance—emerge from this data. Especially for companies lacking an extensive data history, this approach creates a solid foundation for further analysis.

Local data processing in seconds

A key advantage of the i.Cee² is that it processes data directly at the source. Unlike purely cloud-based models, the module utilizes edge computing principles. This reduces data volume, minimizes network dependency, and enables rapid response times. At the same time, integration with higher-level systems remains flexible. Standardized interfaces—such as REST and MQTT APIs—allow data to be transmitted to cloud platforms, SCADA, or MES systems as needed. However, an internet connection is not required; the system operates entirely autonomously in a local setting. The input circuitry for the 24V DC power supply has been proven in numerous industrial applications involving "dirty" power grids and extreme electromagnetic interference (EMI), ensuring stable operation even under challenging electrical conditions—such as on cranes. With the integration of four analog and four digital inputs/outputs, as well as CAN bus, RS485, HDMI, and dual RJ45 ports, the device connects easily to a wide range of commercially available sensors.

Open software for maximum flexibility

Igus also takes an open approach regarding software. The module ships with a ready-to-use environment based on established open-source solutions, including Node-RED (a visual programming tool), InfluxDB (a time-series database), and Grafana (for visualization). This allows users to create initial dashboards, define data flows, and analyze relationships without requiring deep programming expertise. At the same time, the system remains open to expansion—for instance, through additional analysis algorithms or AI-based evaluations.

More information

Spicher Str. 1a
51147 Köln
GERMANY
igus in Social Media:
Share