Data collection and modelling

Data form the basis for use cases such as condition monitoring, diagnosis, predictive maintenance and optimization. Valuable information on wear, causes of faults and optimization potentials are contained in the process data of machines and plants. However, this information often remains unused today because the quantity and complexity of the data is too high and cannot be found by humans without technical support.

We develop solutions for the easy acquisition, management, visualization and analysis of large industrial data sets. For the analysis of the data, methods of machine learning and artificial intelligence are used to train behavioral models. The goal of the models is an automated extraction of information from process data.

Fields of application

In the projects ML4Pro² and CLARA methods are developed and applied to extract large amounts of data from production plants and to train time-dependent behavioral models on the data.

In the project W-Net 4.0 a modular and scalable platform for water supply companies is developed, which can be used for data analysis in addition to GIS system and simulation software. The platform is specially tailored to small and medium-sized enterprises.

For the project ML4Heat, machine learning methods are being developed which optimize the operation of existing district heating networks from an energetic and economic point of view.  For this purpose, mainly sensor and operating data of the district heating transfer stations are used which are merged and evaluated with each other.