The moisture durability of an envelope component such as a wall or roof is difficult to predict. Moisture durability depends on all the construction materials used, as well as the climate, orientation, air tightness, and indoor conditions. Modern building codes require more insulation and tighter construction but provide little guidance about how to ensure these energy-efficient assemblies remain moisture durable. Furthermore, as new products and materials are introduced, builders are increasingly uncertain about the long-term durability of their building envelope designs. Oak Ridge National Laboratory and the US Department of Energy’s Building America Program are applying a rule-based expert system methodology in a web tool to help designers determine whether a given wall design is likely to be moisture durable and provide expert guidance on moisture risk management specific to a wall design and climate. The expert system is populated with knowledge from both expert judgment and probabilistic hygrothermal simulation results.
The design of moisture-durable building enclosures is complicated by the number of materials, exposure conditions, and performance requirements. Hygrothermal simulations are used to assess moisture durability, but these require in-depth knowledge to be properly implemented. Machine learning (ML) offers the opportunity to simplify the design process by eliminating the need to carry out hygrothermal simulations. ML was used to assess the moisture durability of a building enclosure design and simplify the design process. This work used ML to predict the mold index and maximum moisture content of layers in typical residential wall constructions. Results show that ML, within the constraints of the construction, including exposure conditions, does an excellent job in predicting performance compared to hygrothermal simulations with a coefficient of determination, R2, over 0.90. Furthermore, the results indicate that the material properties of the vapor barrier and continuous insulation layer are strongly correlated to performance.
Accompanying efforts worldwide to deploy sustainable building technologies shows a pressing need for expanded research on occupant behavior. Discourse is lacking concerning drivers of occupant behavior for energy conservation, especially in the case of commercial buildings. This paper explores potential determinants of occupant behavior for energy conservation in commercial buildings. This is investigated in a case study of a two-month energy conservation competition involving eight office buildings at the Oak Ridge National Laboratory. Four buildings achieved energy savings based on the previous year’s baseline. Potential challenges and success factors of occupant behavior for energy conservation during the competition were explored based on an explanatory research design incorporating energy data, participant interviews, and surveys. The findings suggest that both social and technological aspects may be important drivers of energy conservation. The determinants of occupant behavior for energy conservation in commercial buildings suggested for further research include bottom-up involvement, stakeholder relationship management, targeted information, real-time energy visualization, and mobile social platforms. This paper presents initial implications, with a need for further research on these propositions and on their impacts on occupant behavior. This paper aims to contribute to both academia and practitioners in the arena of commercial building sustainability.
This work package focused on deploying an instance of the Damara Tern platform to support AMMT collaborative research activities. The objectives were to provide selected AMMT collaborators with access to a shared environment for capturing operations, trackables, and associated metadata, and to implement data entry functionalities that reflect site-specific procedures. Key activities included creating configurable, schema-driven entry forms and validating the data collection process. The report details the deployment process, the platform infrastructure, and the implemented data entry workflows, providing a reference for end users and establishing a foundation for future production-scale deployments.