Utilizing Domain Knowledge: Robust Machine Learning for Building Energy Prediction with Small, Inconsistent Datasets

no code implementations • 23 Jan 2023 • Xia Chen, Manav Mahan Singh, Philipp Geyer

In this study, component-based machine learning (CBML) as the knowledge-encoded data-driven method is examined in the context of energy-efficient building engineering.

Explainable AI for engineering design: A unified approach of systems engineering and component-based deep learning

no code implementations • 30 Aug 2021 • Philipp Geyer, Manav Mahan Singh, Xia Chen

Third, we evaluate explainability by qualitative and quantitative methods demonstrating the matching of preliminary knowledge and data-driven derived strategies and show correctness of activations at component interfaces compared to white-box simulation results (envelope components: R2 = 0. 92.. 0. 99; zones: R2 = 0. 78.. 0. 93).