Predictive Maintenance

We have utilised our experience in the field of big data to find a solution for “predictive maintenance”.

This is only possible with the use of big data technologies, such as recording, storing and analysing large amounts of data. The process derives maintenance information from an object’s data (condition monitoring). The aim is to proactively maintain an object and thus avoid downtimes and minimise costs. In the best-case scenario, faults can be predicted before they have an impact or cause failures.

So what is our solution for this? We have developed the Hahn PRO Time Series Manager. This enables any sensor data to be stored and processed efficiently. If the data collected over a period of time is now linked with artificial intelligence algorithms, predictions can be made.

Hahn PRO Time Series Manager

The challenge is that very large amounts of data are often required to make reliable predictions for predictive maintenance. This data must be recorded, stored and analysed. Due to the huge amounts of data and the many different data and formats, the databases have to provide enormous capacities.

This is why we use techniques and databases from the big data environment in our Hahn PRO Time Series Manager. To analyse the data, it is necessary to access the required values quickly and process them with high performance. The larger the database and the more intelligent and sophisticated the analysis algorithms (neural networks, deep learning or ensemble learning), the more reliable the findings will be. Our Hahn PRO Time Series Manager offers the ideal solution for this.