• Energy Research

ZusammenfassungAuf dem Weg zur Erreichung der gesetzten Klimaziele in Deutschland muss der Anteil erneuerbarer Energien an der Stromerzeugung stetig ausgebaut werden. Die damit einhergehende zunehmende Fluktuation der Erzeugungsleistung stellt die Stromnetze vor große Herausforderungen. Da knapp 44 % des Strom- und rund ein Viertel des Wärmeverbrauchs in Deutschland auf die Industrie entfällt, bietet diese signifikantes Potenzial, Schwankungen im Stromnetz durch die Anpassung des Stromverbrauchs an das Stromangebot im Sinne von Demand Response mittels Energieflexibilität auszugleichen. Bislang erschwert neben regulatorischen Rahmenbedingungen insbesondere eine fehlende einheitliche Modellierung & Kommunikation von Energieflexibilität sowie deren Einbettung in bestehende Unternehmens-IT-Infrastrukturen eine optimale und automatisierte Vermarktung. Im Rahmen des Forschungsprojekts SynErgie wurden hierfür informationstechnische Anforderungen erhoben, Datenmodelle zur Beschreibung von Energieflexibilität und eine übergeordnete IT-Architektur entwickelt. Mit Hilfe einer unternehmensspezifischen Plattform und einer zentralen Marktplattform kann der Informations- und Kommunikationsfluss von der Maschine/Anlage bis zur Flexibilitätsvermarktung und wieder zurück abgebildet werden. Eine Vielzahl verschiedener Services unterstützt hierbei ein Unternehmen von der Identifikation bis hin zur automatisierten und standardisierten Vermarktung von Energieflexibilität. Durch die Einsatzmöglichkeiten und Wirkansätze von IT wurden Grundsteine für nachhaltigkeitsbezogene Effekte des industriellen Energieverbrauchs gelegt, welche in den kommenden Monaten in einer Modellregion in und um Augsburg mit Industrieunternehmen, Netzbetreibern und weiteren Serviceanbietern getestet werden.

Due to the rise of new information and communication technologies manufacturing companies have access to huge amounts of power consumption data which are measured by sensors and processed by information systems. One of the most promising applications of extracting value out of the collected data is the detection of anomalies in process data from industrial machines and equipment. Many research and industry use cases apply machine learning (ML) techniques for anomaly detection. These techniques enable manufacturing companies to optimize their manufacturing processes but also to be more energy efficient and therefore have an impact for sustainable manufacturing. Most of the ML applications use central server infrastructures for data collection from different sources to process and analyse it for further usage. Nevertheless, privacy concerns and security risks motivate manufacturers to store the collected sensitive data from the production line locally. Therefore, suppliers of industrial machines (e.g. robots, machine tools) do not have the possibility, to store and analyse the data in the cloud, where data from all the machines of the supplier in different companies could be analysed and used for ML applications. One of the new paradigm shifts in ML is the concept of federated learning (FL) which enables local devices to use ML without sending data to a central server. This paper introduces an architecture for using the concepts of FL in manufacturing processes enabling machine suppliers to use ML for optimizing machine processes in a collaborative manner. Therefore, the more general federated learning concept is extended for industrial machinery and equipment using the industrial communication framework OPC-UA. Our architecture is tested and validated by using an industrial dataset of different compressors’ power consumption.

Due to the rise of new information and communication technologies manufacturing companies have access to huge amounts of power consumption data which are measured by sensors and processed by information systems. One of the most promising applications of extracting value out of the collected data is the detection of anomalies in process data from industrial machines and equipment. Many research and industry use cases apply machine learning (ML) techniques for anomaly detection. These techniques enable manufacturing companies to optimize their manufacturing processes but also to be more energy efficient and therefore have an impact for sustainable manufacturing. Most of the ML applications use central server infrastructures for data collection from different sources to process and analyse it for further usage. Nevertheless, privacy concerns and security risks motivate manufacturers to store the collected sensitive data from the production line locally. Therefore, suppliers of industrial machines (e.g. robots, machine tools) do not have the possibility, to store and analyse the data in the cloud, where data from all the machines of the supplier in different companies could be analysed and used for ML applications. One of the new paradigm shifts in ML is the concept of federated learning (FL) which enables local devices to use ML without sending data to a central server. This paper introduces an architecture for using the concepts of FL in manufacturing processes enabling machine suppliers to use ML for optimizing machine processes in a collaborative manner. Therefore, the more general federated learning concept is extended for industrial machinery and equipment using the industrial communication framework OPC-UA. Our architecture is tested and validated by using an industrial dataset of different compressors' power consumption.