The goal of the project SePiA.Pro is the development and testing of a standardized, open, cloud-based service platform for the intelligent optimization of a production line in a manufacturing plant. The platform allows small and medium-sized enterprises to offer and use Internet-based services, so-called Smart Services.

Since Smart Services are meant to be portable, the SePiA.Pro project develops an approach to integrate software components together with their runtime environment into a self-describing Smart Service Archive.

The Industrial Analytics Platform developed as part of the SePiA.Pro project is a scalable, cloud-based, distributed runtime environment optimized for processing machine data. It provides the basic functionality (programming languages APIs and libraries) for the creation of Smart Prediction Services and implements the relevant interfaces for the processing and storage of the data, such as the interface to the data exchange service.

The “Industrial Analytics Platform” is based on Apache Flink technology. Apache Flink is a framework and distributed processing engine for stateful computations over unbounded and bounded data streams. Flink has been developed to run in all common cluster environments and perform computations with in-memory speed and at any scale.

In the project, the deployment of the Industrial Analytics Platform has already been successfully demonstrated at TRUMPF’s Smart Factory in Chicago. For this demonstrator a Smart Service for machinery condition monitoring has been developed. Both the Industrial Analytics Platform and the Smart Service can be automatically provisioned using OpenTOSCA and the CSAR packaging format.