Enabling automatic building envelope retrofits using controls and machine learning

Abstract: Buildings contribute to over 35% of the total CO2 emissions in the United States, with 52% of these structures predating the 1980 energy codes. The absence of appropriate thermal insulation in these older structures leads to 20% higher energy use when compared to code-compliant houses. Consequently, retrofitting outdated structures can significantly improve the energy efficiency of the building sector, contributing to the Department of Energy’s goal of achieving net-zero carbon emissions by 2050. New technologies, such as the deployment of panelized insulation over existing envelopes, can increases thermal performance and airtightness with minimal disruptions and a high potential for automation. This talk will explore the research work at Oak Ridge National Laboratory aimed at accelerating the adoption and automation of overclad panel envelope retrofits. The discussion will cover the automated generation of building digital twins using machine learning, real-time tracking of overclad panels with advanced sensing technologies, and the precise automated installation of panels through controls and robotics.

Bio: Dr. Bryan Maldonado is a research staff member in Oak Ridge National Laboratory’s Buildings and Transportation Science Division. He received his BS degrees in mathematics and mechanical engineering from Universidad San Francisco de Quito, Ecuador, in 2014, and his PhD degree in mechanical engineering, with an emphasis on control theory, from the University of Michigan, Ann Arbor, Michigan, USA, in 2019. In 2014, Dr. Maldonado worked as a research assistant at the European Organization for Nuclear Research (CERN) in Geneva, Switzerland. In 2018, he worked as a graduate student research aide at Argonne National Laboratory. He joined the Army Research Laboratory as a journeyman fellow in 2019, and in 2020, he joined Oak Ridge National Laboratory. Dr. Maldonado has coauthored more than 35 publications in the area of dynamics systems and control. His research interests include model-based and model-free identification, estimation, and control of complex dynamic systems with an emphasis on optimal control techniques. Dr. Maldonado is a member of IEEE and a lifetime member of ASME; and the recipient of the 2023 UT-Battelle Early Career Research Accomplishment Award, 2023 Great Minds in STEM Most Promising Scientist Award, and the 2022 ASME Duane P. Jordan Early Career Award.