Predictive maintenance: Establishing predictive maintenance at TRUMPF

Find out how unplanned downtimes were avoided by analyzing machine data and developing a condition monitoring portal. The case study shows how the optimization of service processes and the increase in machine availability were achieved through data-supported solutions.

Let's talk!
icon_Mehrwert

Advantage

Reduction of downtimes, increase in machine availability and optimization of service processes

icon_DataEngeneering

Data

Sensor data from the production machines

icon_Machine-Learning

Method

eoda's empowerment approach combined with a comprehensive data science analytics platform

Challenge

TRUMPF is the global market and technology leader in the field of industrial lasers and laser systems. TRUMPF Laser Technology offers CO2 lasers, solid-state lasers, marking lasers and laser systems.

In order to keep performance and quality high and avoid unforeseen machine failures, predictive maintenance is to be enabled by means of data analysis, thereby increasing the quality and availability of machine performance.

Digitaler Zwilling TRUMPF

Goal

The realization of the predictive maintenance approach and the fundamental increase of the digital maturity level based on data and algorithms: These two overarching goals were TRUMPF's driving force before the project with eoda began.

To achieve them, the two partners defined the following milestones:

  • Introduction of data science for the exploratory use of data
  • Analysis of lasers, whose sensors and system messages produce countless machine data every day
  • Introduction of algorithms for pattern recognition of error patterns and forecasting future failures
  • Transparent and clear visualization of machine data
  • Introduction of cross-role and cross-departmental workflows to support business processes between development, service, after sales and external and internal data scientists

Solution

As a first step, eoda helped TRUMPF to train its own data science team. The trained team thus combined domain knowledge and data expertise. This enabled it to quickly identify and implement the first data science use cases successfully. TRUMPF used the leading data science programming language R to carry out the complex analyses of the machine data.

The implemented use cases consisted of evaluating the existing machine data sets, analyzing them for anomalies and failures, mapping the results and predicting future problems.

Beispiel-Dashboard des Condition Monitoring Portals: Anzeige der entsprechenden Anlagen.

Widget zum Optimieren der Analyseergebnisse.

Das Condition Monitoring Portal bietet TRUMPF die Möglichkeit, Dashboards selbst zu erstellen und anzupassen.

Beispiel einer Anomalie-Erkennung in Sensordaten (rote Markierung).

The specialist departments and management involved were won over by the results of the analyses. In the further course of the project, the focus was on integrating data science into the existing business processes. To this end, a condition monitoring portal was developed on the basis of the eoda analytics platform.

The condition monitoring portal makes it possible to monitor the condition of the machines and optimize the effort and costs of maintenance in the context of predictive maintenance. The portal is an on-premise solution: TRUMPF retains complete control over the data and algorithms.

"eoda has enabled us to rectify problems before they actually occur. Thanks to real-time data analysis, we reduce downtimes, optimize processes and increase machine availability at the same time."

Marco Holzer | Leiter Produktmanagement & Logistik Services | TRUMPF

Trumpf Testimonial Marco Holzer

Result

eoda has supported TRUMPF from the development of expertise to the solution going live, laying the foundation for data-driven business models.

At its heart, the Condition Monitoring Portal brings data, analyses and results into daily business processes, thus sustainably increasing TRUMPF's data-centricity. The information contained in the machine data becomes tangible - from development to service and after-sales. The Condition Monitoring Portal connects different departments, teams and roles through intuitive workflows, enabling them to work together on data science use cases.

This makes it possible to create new data-based services, such as the realization of predictive maintenance. This enables TRUMPF to detect machine malfunctions in advance and thus further increase the availability of its machines. The successful implementation of this use case is driving many other digital initiatives at TRUMPF.

Get started now:
We look forward to exchanging ideas with you.

Kontakt_final_Mastmeyer

Your expert on Data-Science-Projects:

Lutz Mastmayer
projects@eoda.de
Tel. +49 561 87948-370







    Scroll to Top