The goal of the CEMTEC-FIWARE project was to implement a FIWARE based condition monitoring and expert system platform at the CEMTEC cement milling pilot plant in Enns, Austria. A system has been put in place that automatically records process measurements and operator set-points during batch-production in a cloud database. Methods and tools for data analysis and the concept of a physics based and data driven expert system have been developed and prepared for future deployment. Once enough production data is collected, this expert system can be calibrated with it; it will then suggest set-points to the pilot-plant operators, with the aim of these set-points being optimal for energy efficient cement production.
The condition monitoring and expert system platform is built around FIWARE components running in pods on a cloud server. Administration of the containers is performed using Kubernetes. Connection to PLCs and installed sensors is realized via the industry standard OPC-UA using a secure LTE connection. Production data and set points are stored in a database (crateDB) using QuantumLeap and visualized with the open source tool Grafana.
Key features and benefits of the developed platform are:
For LCM, the acquired know-how regarding cloud based FIWARE implementations together with the developed framework for condition monitoring, process modeling and generation of expert systems allows to offer similar solutions to LCM customers in different industries. The cloud-centric implementation allows LCM to directly reuse the implementation work done in CEMTEC-FIWARE, acting as an enabler for data analytics and AI projects.
For company partner CEMTEC, the pilot plant FIWARE implementation for condition monitoring, data storage and data analytics will help to efficiently acquire new insights into the cement grinding process, required for competitive product development.