Big Data for Factories How can data from production be used to predict and prevent machine breakdowns? This was the subject of a pilot factory in the leading-edge cluster it's OWL, which BENTELER and Fraunhofer IEM set up in Paderborn. It is part of the EU project BOOST 4.0 on the topic of Big Data in industry, which was launched with representatives of the European Commission in Boroa (Spain) at the end of January.

Detecting machine errors before they happen

Networked pilot factories are being set up at ten European locations, for example in Spain, Italy, Sweden and also at the BENTELER plant in Paderborn, where initial projects relating to industrial data analysis and utilization are being tested and implemented. The pilot factories are the linchpin of the EU research project BOOST 4.0, which aims to promote the Europe-wide exchange and standardization of Big Data in industry with 50 partners.



"Much of the data generated in manufacturing is volatile and remains unused," explains Sebastian von Enzberg, senior expert for Industrial Data Science at Fraunhofer IEM. "In order to create value from them, data must be able to be provided with contextual information, stored persistently, and exchanged securely. Data analysis itself must contribute to value creation and requires structural transformations of business processes. BOOST 4.0 lays technological foundations for the successful Europe-wide implementation of the Industry 4.0 strategy." 

Predictive maintenance model

The Fraunhofer IEM is developing a process model for the implementation of predictive maintenance, such as maintenance and inspection of machines to avoid operational failures. For this purpose, data-driven modeling methods (machine learning methods) are used and further developed, which, for example, detect machine faults before they happen. Together with project partner Benteler, one of the ten lighthouse factories will be built in Paderborn by 2020, where the developed methods and models will be implemented and tested. The leading-edge cluster it's OWL is contributing its experience in the area of technology transfer. Thus, the experience and results are made available through targeted activities for the partners in the technology network.



Together with Fraunhofer IEM, Benteler developed a model for predictive maintenance of machines using Big Data. Benteler is now putting the process model into practice. In this way, production stops can be avoided and customers can be supplied on time and at fair prices. "Thanks to Boost 4.0, we have significantly improved our Big Data infrastructure. And we are reaching the next level of data analytics within Benteler. The project is a driver to increase our competence in Industry 4.0. As a direct benefit, it has increased the overall plant effectiveness of the machines considered by five percent. The next step is to transfer the project results to all BENTELER plants worldwide. This will enable us to meet our customers' requirements faster, more reliably and with even higher quality," Emerson Galina, COO Benteler Automotive, summarizes the results after successful project completion.



The Fraunhofer IEM, Benteler and it's OWL are partners in the EU project BOOST 4.0, one of the largest European initiatives for Big Data in industry. Existing German reference architectures such as RAMI 4.0 or the Industrial Data Space are being incorporated into the development of European Big Data standards. Methods and models are being linked and various communities and experiences from Europe are being brought together. The three-year project involves 50 companies (including Phillips, Siemens, Volvo and IBM) from 16 countries. The project volume includes funding of around 20 million euros from the European Commission and investments of 100 million euros by the participating companies. The BOOST 4.0 project is funded by the European Union's Horizon 2020 research and innovation program.