skip to main content


Title: An Instance Segmentation and Clustering Model for Energy Audit Assessments in Built Environments: A Multi-Stage Approach
Heat loss quantification (HLQ) is an essential step in improving a building’s thermal performance and optimizing its energy usage. While this problem is well-studied in the literature, most of the existing studies are either qualitative or minimally driven quantitative studies that rely on localized building envelope points and are, thus, not suitable for automated solutions in energy audit applications. This research work is an attempt to fill this gap of knowledge by utilizing intensive thermal data (on the order of 100,000 plus images) and constitutes a relatively new area of analysis in energy audit applications. Specifically, we demonstrate a novel process using deep-learning methods to segment more than 100,000 thermal images collected from an unmanned aerial system (UAS). To quantify the heat loss for a building envelope, multiple stages of computations need to be performed: object detection (using Mask-RCNN/Faster R-CNN), estimating the surface temperature (using two clustering methods), and finally calculating the overall heat transfer coefficient (e.g., the U-value). The proposed model was applied to eleven academic campuses across the state of North Dakota. The preliminary findings indicate that Mask R-CNN outperformed other instance segmentation models with an mIOU of 73% for facades, 55% for windows, 67% for roofs, 24% for doors, and 11% for HVACs. Two clustering methods, namely K-means and threshold-based clustering (TBC), were deployed to estimate surface temperatures with TBC providing consistent estimates across all times of the day over K-means. Our analysis demonstrated that thermal efficiency not only depended on the accurate acquisition of thermal images but also relied on other factors, such as the building geometry and seasonal weather parameters, such as the outside/inside building temperatures, wind, time of day, and indoor heating/cooling conditions. Finally, the resultant U-values of various building envelopes were compared with recommendations from the American Society of Heating, Refrigerating, and Air-conditioning Engineers (ASHRAE) building standards.  more » « less
Award ID(s):
1920011
NSF-PAR ID:
10297574
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
Sensors
Volume:
21
Issue:
13
ISSN:
1424-8220
Page Range / eLocation ID:
4375
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract One of the major challenges in the development of micro-combustors is heat losses that result in flame quenching, and reduced combustion efficiency and performance. In this work, a novel thermal barrier coating (TBC) using hexagonal boron nitride (h-BN) nanosheets as building blocks was developed and applied to a Swiss roll micro-combustor for determining its heat losses with increased temperatures inside the combustor that contributes to improved performance. It was found that by using the h-BN TBC, the combustion temperature of the micro-combustor increased from 850 K to 970 K under the same thermal loading and operational conditions. This remarkable temperature increase using the BN TBC originated from its low cross-plane thermal conductivity of 0.4 W m−1 K−1to mitigate the heat loss from the micro-combustor plates. Such a low thermal conductivity in the h-BN TBC is attributed to its interfacial resistance between the nanosheets. The development of h-BN TBC provides an effective approach to improve thermal management for performance improvements of gas turbine engines, rocket engines, and all various kinds of micro-combustors. 
    more » « less
  2. Many researchers have studied the roles of building envelope materials on UHI, such as roofs, and walls, but few of them have explored the impacts of the emergence of the solar-reflective coatings, films, and panels but well-visible transmittance that is increasingly applied to glazed building facades, especially in hot climates, for outdoor thermal environments. The question then arises: Despite the positive effects of these strong solar-reflective facades on building heating and cooling energy savings, do they have the same positive effects on the adjacent outdoor area, especially in a dense urban context? This research aims to quantify the potential UHI effects of the solar-reflective facades relative to the non-reflective ones in a dense urban context, along with the heating and cooling energy performance analysis. As such, a simulation method in terms of a series of tools including LBNL Radiance, EnergyPlus, and WINDOW software was adopted in this work to analyze the solar radiation interactions between the façade surface and the surrounding urban structures and potential temperature rise under solar-reflective and non-reflective facades. The result shows that the annual cooling energy savings by using the solar-reflective facades are about 33.8% relative to the typical double-pane clear glazed façade because of the substantial reduction of U-factor and solar heat gains; But, this preliminary work also unveils the potential adverse effects of using such materials at the urban scale, leading nearly 2 times greater solar irradiation and UHI effects than the ones by the solar-non-reflective building surfaces in an urban area. Future optimization studies on the trade-off between the building cooling energy savings and UHI effects by the solar-reflective façades need to be conducted. 
    more » « less
  3. null (Ed.)
    The photothermal experiments on the incident light angle dependence are carried out using simulated solar light on thin films of both iron oxides (Fe3O4 and Fe3O4@Cu2-xS) and porphyrin compounds (chlorophyll and chlorophyllin). Fe3O4 and Fe3O4@Cu2-xS are synthesized using various solution methods that produce mono-dispersed nanoparticles on the order of 10 nm. Chlorophyll is extracted from fresh spinach and chlorophyllin sodium copper is a commercial product. These photothermal (PT) materials are dispersed in polymethyl methacrylate (PMMA) solutions and deposited on glass substrates via spin coating that result in clear and transparent thin films. The iron-oxide based thin films show distinctive absorption spectra; Fe3O4 exhibits a strong peak near UV and gradually decreases into the visible and NIR regions; the absorption of Fe3O4@Cu2-xS is similar in the UV region but shows a broad absorption in the NIR region. Both chlorophyll and chlorophyllin are characterized with absorption peaks near UV and NIR showing a “U”-shaped spectrum, ideally required for efficient solar harvest and high transparency in energy-efficient single-pane window applications. Upon coating of the transparent PT films on the window inner surfaces, solar irradiation induces the photothermal effect, consequently raising the film temperature. In this fashion, the thermal loss through the window can be significantly lowered by reducing the temperature difference between the window inner surface and the room interior, based on a new concept of so-called “optical thermal insulation” (OTI) without any intervention medium, such as air/argon, as required in the glazing technologies. Single-panes are therefore possible to replace double- or triple panes. As OTI is inevitably affected by seasonal and daily sunlight changes, an incident light angle dependence of the photothermal effect is crucial in both thin film and window designs. It is found that the heating curves reach their maxima at small angles of incidence while the photothermal effect is considerably reduced at large angles. This angle dependence is well explained by light reflection by the thin film surface, however, deviated from what is predicted by the Fresnel’s law, attributable to non-ideal surfaces of the substrates. The angle dependence data provides an important reference for OTI that window exposure to sun is greater at winter solstice while that is considerably reduced in the summer. This conclusion indicates much enhanced solar harvesting and heat conversion via optically insulated windows in the winter season, resulting in much lower U-factors. 
    more » « less
  4. Abstract

    Heat transport across vertical interfaces of heterogeneous 2D materials is usually governed by the weak Van der Waals interactions of the surface‐terminating atoms. Such interactions play a significant role in thermal transport across transition metal carbide and nitride (MXene) atomic layers due to their hydrophilic nature and variations in surface terminations. Here, the metallicity of atomically thin Ti3C2TzMXene, which is also verified by scanning tunneling spectroscopy for the first time, is exploited to develop a self‐heating/self‐sensing platform to carry out direct‐current annealing experiments in high (<10−8bar) vacuum, while simultaneously evaluating the interfacial heat transport across a Ti3C2Tz/SiO2interface. At room temperature, the thermal boundary conductance (TBC) of this interface is found, on average, to increase from 10 to 27 MW m−2K−1upon current annealing up to the breakdown limit. In situ heating X‐ray diffraction and X‐ray photo‐electron spectroscopy reveal that the TBC values are mainly affected by interlayer and interface spacing due to the removal of absorbents, while the effect of surface termination is negligible. This study provides key insights into understanding energy transport in MXene nanostructures and other 2D material systems.

     
    more » « less
  5. ABSTRACT To understand the potential impacts on both thermal performance and condensation risks of using low-e coatings in buildings, especially in the single-pane sector, in this work, parametric numerical analysis in winter is conducted. Three building glazing models, including the single-pane without low-e coatings (SNL), single-pane with exterior low-e coatings (SEL), and single-pane with interior low-e coatings (SIL), are selected and simulated through COMSOL over a range of outdoor temperature and indoor humidity. The temperature of the interior surface of windows, heat flux through windows, winter U-factor of center-of-glass will be obtained and compared. Additionally, a numerical code is developed in R to compute and plot the condensation temperatures of these three models upon the given indoor humidity levels and simulated surface temperatures. The comprehensive analysis of condensation risks on the glazing inner surface of the three models will be conducted. This parametric simulation effort indicates an interesting feature for a single-pane window: while the SIL gives a substantially lower U than the SNL, it also corresponds to an increased condensation risk under certain limits of external temperature and indoor humidity levels. Upon the resultant condensation temperatures and thermal performance analysis, we can conclude the parameters of the windowpane property, coating emissivity and placement, local climate, and building interior thermal settings must be taken into account collectively when it comes to adding low-e coatings to single-pane windows. 
    more » « less