Reducing configuration efforts in energy management systems based on natural language processing methods and asset administration shells

Energy management systems are an important tool for increasing the energy efficiency of buildings. However, the widespread availability of such systems is offset by the complexity and high costs of implementation, as well as a lack of data. These obstacles can be addressed by using standardized digital twins of technical components. In combination with homogeneous semantics and standardized interfaces as uniform access points to information, the implementation of an energy management system can be simplified. However, given the large number of different manufacturers of the technical components, an agreement on a common semantic standard of the information elements seems unlikely. Studies show that methods from the field of natural language processing can be used to process heterogeneous semantics. An agreement on a common vocabulary is no longer necessary. Instead, different semantics can be used and matched to a target vocabulary. The implementation of such a matching service reduces the configuration effort for the implementation of an energy management system. Providing an Industrie 4.0 interface that contains the semantic matching service within the components allows the interaction between them and an energy management system. A prerequisite for automated interaction is the availability of information in a uniform structure in the form of an information model. This paper presents the design of an Industrie 4.0 asset administration shell and initial submodels for an energy management system. Additionally, an Industrie 4.0 interface for the semantic matching service is implemented in a prototypical application of an energy management system. This implementation demonstrates how the configuration effort of such a system can be reduced by semantic matching.