Efficiency

The University of Michigan-Dearborn will develop a machine learning-enhanced design tool for the automated architectural configuration and performance evaluation of electrical power converters. This tool will help engineers consider a wider range of innovative concepts when developing new converters than would be possible via traditional approaches.

Pacific Northwest National Laboratory (PNNL) will apply multiple machine learning tools to develop next-generation natural gas to electric power conversion system designs. The project leverages a physics-informed machine learning tool for automated reduced order model (ROM) construction. This will significantly reduce prediction errors compared to traditional approaches.

The Massachusetts Institute of Technology (MIT) will develop a machine learning (ML) approach to optimize surfaces for boiling heat transfer and improve energy efficiency for applications ranging from nuclear power plants to industrial process steam generation. Predicting and enhancing boiling heat transfer presently relies on empirical correlations and experimental observations. MIT’s technology will use supervised ML models to identify important features and designs that contribute to heat transfer enhancement autonomously.

Julia Computing, Inc. will develop a neural component machine learning tool to reduce the total energy consumption of heating, ventilation, and air conditioning (HVAC) systems in buildings. As of 2012, buildings consume 40 percent of the nation’s primary energy, with HVAC systems comprising a significant portion of this consumption. It has been demonstrated that the use of modeling and simulation tools in the design of a building can yield significant energy savings—up to 27 percent of total energy consumption. However, these simulation tools are still too slow to be practically useful.

Led by Dr. YuHuang Wang, the “Meta Cooling Textile (MCT)” project team at the University of Maryland (UMD) is developing a thermally responsive clothing fabric that extends the skin’s thermoregulation ability to maintain comfort in hotter or cooler office settings. Commercial wearable localized thermal management systems are bulky, heavy, and costly. MCT marks a potentially disruptive departure from current technologies by providing clothing with active control over the primary channels for energy exchange between the body and the environment.

Stony Brook University will develop eSAVER, an active air conditioning vent capable of modulating airflow distribution, velocity, and temperature to promote localized thermal envelopes around building occupants. Stony Brook’s smart vent modulates the airflow using an array of electro-active polymer tubes that are individually controlled to create a localized curtain of air to suit the occupant’s heating or cooling needs.

Stanford University will develop transformative methods for integrating photonic, or radiant energy structures into textiles. Controlling the thermal photonic properties of textiles can significantly influence the heat dissipation rate of the human body, which loses a significant amount of heat through thermal radiation. To achieve heating, the team utilizes metallic nanowire embedded in textiles to enhance reflection of body heat. To achieve cooling, the team utilizes visibly opaque yet infrared transmissivity (IR) transparent textile.

The University of California, San Diego (UC San Diego) will develop smart responsive garments that enable building occupants to adjust their personal temperature settings and promote thermal comfort to reduce or eliminate the need for building-level air conditioning. The essence of building energy savings in UC San Diego's approach is based on the significant energy consumption reduction from the traditional global cooling/heating of the whole room space. This is done via localized cooling and heating only in the wearable structure in the very limited space near a person’s skin.

The University of California, Irvine (UC Irvine) will develop a dynamically adjustable thermoregulatory fabric. This fabric leverages established heat-managing capabilities of space blankets and color-changing polymers inspired by squid skin that will provide wearers with the unique ability to adaptively harness their own individual radiant heat production. This technology holds the potential to establish an entirely new line of personal apparel and localized thermal management products that could significantly reduce the energy required to heat and cool buildings.

Syracuse University will develop a near-range micro-environmental control system transforming the way office buildings are thermally conditioned to improve occupant comfort. The system leverages a high-performance micro-scroll compressor coupled to a phase-change material, which is a substance with a high latent heat of fusion and the capability to store and release large amounts of heat at a constant temperature. This material will store the cooling produced by the compression system at night, releasing it as a cool breeze of air to make occupants more comfortable during the day.