Ontology-Based Expert System for Automated Monitoring of Building Energy Systems
Hervé Pruvost, Andreas Wilde, Olaf Enge‐Rosenblatt
Abstract
Modern buildings have complex technical equipment that is hard to operate efficiently from a user’s point of view. Users and building managers therefore need guidance in terms of finding the most efficient operational strategies and monitoring plans to avoid faults and energy wastes. Current support systems can do that, but they must usually be adapted to each building manually. In this study, an expert system is proposed that provides a complementary analysis layer with semantic modeling and knowledge reuse. During the configuration phase, the system starts from a semantic description of a building energy system to identify potential efficiency risks and automatically apply generic monitoring functions and rules for building operation. In the operational phase, it generates advices based on continuous real-time analysis of building operational data. The current implementation of the expert system in 14 buildings proved that the approach can allow for a deployment on a larger scale.