Data analytics is the logical consequence of our work as engineers. The increasing availability of data down to a component level provides new opportunities for system monitoring and prediction. System performance and failures become predictable and can be prevented.

Our data-driven approach offers new service models and business opportunities over the entire product life-cycle. State-of-the-art analysis tools are a requirement. Our basis will be both a sound understanding of the physics and the data based product life-cycle analytics.


The impact of data-driven analysis and the power of self-learning algorithms on technical equipment can be dramatic. Even in relatively small systems, performance parameters and events are detected that would remain hidden from a conventional physical analysis. Performance can be monitored and predicted and failures can be prevented. But while we are convinced that data science is revolutionizing engineering, we firmly believe that a sound knowledge of the physics, the operation and the product life cycle is still required and will be so for a long time. New service strategies and business models can only emerge from a thorough understanding of the product.

We have assembled a team of experienced life-cycle and service strategies experts, thermo- and fluid dynamic engineers and data scientists to follow this approach consequently. Together with our customers, we implement this technology and methods and develop business new opportunities.


Data science and analytics

Our experience includes consulting and development of data science projects. We focus on the development of tailored solutions in the areas of event classification, anomaly detection, statistical inference based optimization, database architecture and improvement of machine-learning algorithm accuracy.

We work with state of the art tools and adapt to the technological ecosystem & requirements of our clients. Data analytics enables a full data-driven understanding of the system under investigation. Furthermore, it opens the possibility to optimize it’s performance, predict it’s behavior and detect abnormal conditions. We develop predictive, descriptive and decisive models and select the right algorithm for your specific life cycle solution.

Product life cycle analysis

Prediction and prognostics on machine level data is a key capability for OEMs and allows new business models for your product services. The correlation of machine data with fleet data (e.g. maintenance events, service events, manufacturing and production events) defines valuable predictive services and increases quality and life-cycle performance. Also the comparison and learning from the product fleet with pattern detection will generate valuable service events and improve your product operations. New monitoring and diagnosis systems based on data analytics will supervise your product performance during the life cycle.

Sensor technology

In all our projects sensors or sensor data have played an important part. We have developed both wired and wireless sensors for specific customer applications or measurement campaigns. We have temporarily or permanently instrumented technical systems and developed the necessary data acquisition and processing hard- and software. With all this activity, we know what to expect from a sensor, how to interpret the available data and, most importantly, which signal can be trusted and which not. We are capable to differ between the signature from a physical event and the effect from an ill placed or not adapted sensor.

This puts us in the perfect position to assess and characterize the available sensors and sensor data and put the different readings into perspective.

System modelling

We start with the increase of data quality with the right data munging strategy, as conversion, transformation, merging, and the detection of missing or anomalous data, all are critical for the system modelling.

We routinely work with a model of the system. On many occasions the physical understanding gained through modelling has been critical to identify the relevant system parameters and conditions based on our data analytics.

The output of a model turns on the quality of the input. The important part is to formulate the right questions, to assess possible answers with the model and to process and present the data. The understanding of a system is only sufficient, if the governing mechanisms can be presented simply and are intuitively clear. This is where know-how and experience come in.