| | | | | |
Background, Interest,
and Capabilities | |
| | |
| | | | |
 | Loading… |
|
| Loading… |
| | |
| Loading… |
|
| | University of Debrecen | Netsanet Anteneh Ferede | |
Academic
|
Other Energy Technologies
| Fluid flow mechanics,Design |
| |
| | North Carolina A&T State University | Evelyn Sowells-Boone | |
Academic
|
Other Energy Technologies
| Dr. Evelyn R. Sowells-Boone is an Assistant Professor in the Computer Systems Technology department at North Carolina A&T State University’s College of Science and Technology. Prior to joining the School of Technology faculty, she held positions at U.S. Department of Energy, N.C. A&T’s Division of Research and College of Engineering. Dr. Sowells earned a Ph.D. in Electrical Engineering from North Carolina A&T State University’s College of Engineering. She also holds a M.S. and B.S in Computer Science with a concentration in software engineering. Her primary research interests are in the areas of low-power digital systems design, self-timed digital system design and STEM education. Her primary research interests are in the areas of efficient electronic systems design and STEM education. As a result of her work, she has numerous peer reviewed journal and conference publications. She recently authored a book entitled “Low Power Self-Timed Size Optimization for an Input Data Distribution,” which explores innovative techniques to reduce power consumption for portable electronic devices. Her current research project is the “Smarter Phone” which operates using a power saving application that profiles the users’ daily routine and location then customizes a unique battery power saving scheme. The results are more than promising, saving 3% battery power or 43 minutes of battery life in a 24 hour period. As a result of her research in the past years, she was awarded the 2016 Chair’s award for Junior Researcher of the year in the Computer System Technology department, as well as a 2016-2017 College of Science and Technology Research Rookie of the Year Merit Award. To date she has $2,752,850.00 in research funding. |
| NC |
| | National Renewable Energy Laboratory (NREL) | Donal Finegan | |
Federally Funded Research and Development Center (FFRDC)
|
Other Energy Technologies
| I specialize in diagnostics of Li-ion batteries, from the materials level using X-ray and electron microscopy techniques, to the system level using thermal and electrochemical techniques. During my PhD I pioneered the field of high-speed X-ray imaging to characterize failure mechanisms of Li-ion batteries during thermal runaway which led to a joint position with NASA and NREL on understanding the safety risks associated with battery failure. I now work on developing lab-based characterization techniques that can be used to predict the lifetime and performance of Li-ion battery materials, for which ML has become an integral part. |
| CO |
| | University of Central Florida | Felipe A. C. Viana | |
Academic
|
Power Generation: Renewable
| Dr. Felipe Viana is an assistant professor at the Department of Mechanical and Aerospace Engineering at UCF. The vast majority of Dr. Viana's work has been applied to new designs and the improvement of fielded products with a focus on aircraft propulsion, power generation, and oil and gas systems. Over the years, his research has generated a number of peer-reviewed publications and patents. He serves as review editor for Structural and Multidisciplinary Optimization and as a reviewer in top journals and conferences.
Before joining UCF, Dr. Viana was a senior scientist at GE Renewable Energy, where he led the development of state-of-the art computational methods for improving wind energy asset performance and reliability. Prior to that, he spent five years at GE Global Research, where he lead and conducted research on services engineering, design and optimization under uncertainty, and probabilistic analysis of engineering systems.
Products of my research relevant to this opportunity:
- https://github.com/PML-UCF
- R. G. Nascimento and F. A. C. Viana, "Fleet prognosis with physics-informed recurrent neural networks," arXiv preprint, arXiv:1901.05512, 2019.
- F.A.C. Viana and A.K. Subramaniyan, "Massively accelerated Bayesian machine," Filed on Jan 09, 2017, Published on July 12, 2018, Publication number US20180196892A1.
- A.K. Subramaniyan, K.M.K. Genghis Khan, F.A.C. Viana, and N.C. Kumar, "Systems and methods for predicting asset specific service life in components," Filed on Dec 31, 2015, Published on Jul 6, 2017, Publication number US20170193460A1.
- A. Dourado, F. Irmak, F.A.C. Viana, and A.P. Gordon, "A Bayesian framework for estimation of strain life lower bounds and its application to IN617," Proceedings of ASME Turbo Expo 2019: Turbomachinery Technical Conference and Exposition, Phoenix, USA, June 17-21, 2019, GT2019-91958.
- Y. A. Yucesan and F.A.C. Viana, "Onshore wind turbine main bearing reliability and its implications in fleet management," AIAA SciTech Forum, San Diego, USA, January 7-11, 2019, AIAA 2019-1225. |
| FL |
| | Private person | Alexander Ivanovich Khripkov | |
Individual
|
Other Energy Technologies
| The theoretical substantiation of cyclic processes of structural formations of known matter allows us to isolate the necessary compositions of functional complexes due to the distribution of phase transitions. These data constitute an extensive functional base of the structures of the main isotopes contained in the cyclic mathematical table of nuclear symbols.
“The mathematical table of chemical symbols” (page. 35). https://internauka.org/archive2/internauka/7(89_2).pdf
The main definition of phase transitions and formations of nuclear structures is the process of formation of a functional charge, containing all possible phase combinations in different periods of time. In this case, practical research results confirm the author's hypothesis about the technical possibility of the cyclical formation of phase transitions in real time.
https://youtu.be/tgR6vpqAYEY
Such primitive experiments were carried out in various conditions using technical and biological waste. In particular, for motor fuel, the established cycle performs the transition of two phases liquid-gas-liquid in real time. This technology can significantly reduce the mechanical part of any engine.In favorable conditions of the technical scientific base and financing, as part of the relevant project group, these data can reach a decent industrial level of modern energy technologies.
“The causes and conditions of the formation of the functional structure of Hydrogen” (page. 31)
https://internauka.org/archive2/internauka/6(88_2).pdf
“The Gravitational structure of the degree of motion of the functional composition of the volume of time, phase cycles of the basic functions of space” (page. 45)
https://internauka.org/archive2/internauka/7(89_2).pdf |
| |
| | C3.ai | Carlton Reeves | |
Small Business
|
Other Energy Technologies
| C3.ai is a leading enterprise AI software provider for accelerating digital transformation. C3.ai delivers a comprehensive and proven set of capabilities for rapidly developing, deploying, and operating large scale AI, predictive analytics, and IoT applications for any enterprise value chain in any industry. The C3 AI Suite and C3.ai applications are proven and tested at petabyte scale, solving previously unsolvable challenges. At the core of the C3 AI Suite is a revolutionary and powerful model-driven AI architecture that dramatically enhances the productivity of data scientists and application developers while future-proofing applications against underlying IT evolution. The C3 AI Suite is 10 to 100x faster and more reliable than other solutions or DIY approaches, enabling robust delivery of production applications with 100x less code and cost. The C3 AI Suite seamlessly works with existing data storage, sources, tools, and infrastructure investment, while flexibly operating in a private, hybrid cloud, or multi-cloud environment. The C3 AI Suite supports configurable, pre-built, high value AI applications for predictive maintenance, fraud detection, sensor network health, supply chain optimization, energy management, anti-money laundering, and customer engagement. www.c3.ai |
| CA |
| | MCE Nexus | Christopher Taylor | |
Small Business
|
Other Energy Technologies
| MCE Nexus provides sustainable, resilient and integrated solutions for the industrial co-production of materials, chemistry and energy by finding common platforms that maximize efficiency and minimize waste streams. Meeting the needs of current and future generations without damaging our biosphere beyond repair requires a transformation in the way materials, chemicals and energy are produced, utilized and maintained in the industrial economy. MCE Nexus takes a circular economy approach to industrial production, aiming for closed loop or nearly closed loop systems that value products according to their materials, chemical and energy content. Examples include platforms that favor co-production, such as molten salt working fluids for energy production and electrochemical refining, and chemical processes that maintain solvent reuse.
MCE Nexus uses thermodynamic and kinetic modeling, along with first-principles simulation and data informatics, to seek out optimal synthesis and processing routes for the necessary materials and chemicals required to build closed-loop industrial processes for co-production of energy, fuels and other storage media, chemical reagents, as well as structural and functional materials. Our experience in atomistic modeling of materials and interfaces, molecular simulation, first-principles thermodynamic and kinetic modeling, and machine learning, provides the capability to explore new chemical and materials systems and routes de novo. MCE Nexus is working to fast track the process by development of Automated Chemical and Materials Intelligence (ACMI): a platform for searching out and identifying optimal schemes for connecting raw materials and by-products with production objectives while minimizing waste and the use of toxic or dangerous chemicals and materials. |
| OH |
| | Clir Renewables | Gareth Brown | |
Small Business
|
Power Generation: Renewable
| Clir Renewables develops AI software that improves the performance, profitability, and lifespan of renewable generation technologies, such as wind turbines and solar panels. By stitching together misaligned production/event data and enriching the outcome with both meteorological/grid conditions and contractual information (e.g. service agreements), our pipeline puts turbines into their environmental, historical, and financial contexts. This data-synthesis and enrichment provides accurate and comprehensive visibility of turbine performance, empowering operators to quickly make cost-saving decisions.
Specialties include:
- wind power engineering
- predictive component failure analytics
- wind to power forecasting
- big data, and database design
- machine learning
- lost energy modeling
- cloud infrastructure
- wind farm permitting/contracting landscape
- site suitability analysis
- turbine icing control
- SCADA connection/retrieval |
Website: clir.eco
Email: gareth@clir.eco
Phone: +1 (604) 262 2009
Address: 2021 Columbia St, Vancouver, British Columbia, V5Y 3V6, Canada
| British Columbia |
| | Ampcera Inc. | Hui Du | |
Small Business
|
Other Energy Technologies
| Ampcera Inc. is the leading company in commercialization of high-performance solid-state electrolytes. Ampcera is committed to supporting the battery research/development community with the best quality of solid-state materials and processing solutions. We have been supplying solid state electrolyte to more than 100 battery research entities globally.
Ampcera product include the following:
1. Oxide solid state electrolytes: Garnet Structure LLZO with different dopants. LiSICON LAGP glass ceramics.
2. Sulfide solid state electrolytes: argyrodite Li6PS5(Cl, Br, I), LGPS, LSPS, Li3PS4, Li7P3S11 etc.
We supply these materials in kilogram level with customized properties.
Ampcera technologies include high throughput roll-to-roll processes to make ceramic-polymer composite electrolyte that can be integrated easily with battery production. We also develop low cost novel structure solid state electrolyte membranes for lithium extraction and spent battery recycling.
Ampcera Technical Team include material and battery scientists with many years of expertise in inorganic/organic material synthesis, processing, composite processing, and battery development.
Ampcera is well equipped for solid state synthesis using conventional and non-conventional approaches, composite process, roll-to-roll process.
We are interested in machine learning based approaches for high-performance solid-state electrolyte discovery and development on both molecular level and material processing level. We are interested in teaming up with partners with complimentary skills, such as theory calculation, process automation, and battery design and testing, data mining and algorithm, to apply for this upcoming ARPA-E funding opportunity. |
| AZ |
| | Ciclos | Juan Zausen | |
Small Business
|
Power Generation: Renewable
| We have been working on renewable energies for the past 7 years and working closely with various universities both in Europe and the US. Our expertise is in manufacturing advances renewable energy products. |
| |
| | University of Rochester | Subhash Singh | |
Academic
|
Building Efficiency
| We are developed and pioneered superwicking metal technology where water and fluids uphills the vertically mounted surface with unprecedented high speed through strong capillary action. We are using our superwicking surface technology in the development of energy efficient ACs, pumpless transport of water and other-fluid, in HVAC, in active cooling of power electronics and computers, and so on. A focussed beam from Femtosecond laser is used to write microcapillary and covers its surface with a range of nano/microparticles to create a hierarchical structure. Aspect ratio (depth/width) of capillary, size, and distribution of nano/microstructure on the wall of microcapillaries and type of materials determine the speed of fluid transport on the surface. By varying laser and material parameters, we are making a library for the depth and surface profile of micro-capillary using 3D microscopy and scanning electron microscopy and corresponding water uphill and transport speed to train the machine. Through inverse design, we would be able to set experimental laser parameters for a given material that can provide a desired uphill speed. Performing this research on electro-active polymers, we can tune the surface profile and roughness of capillary by an electric field to control fluid flow rate on a vertically mounted or tilted surface. |
| NY |
| | Arizona State University | Houlong Zhuang | |
Academic
|
Power Generation and Energy Production: Liquid and Gaseous Fuels/Nuclear
| My group focus on applying machine learning to design energy-related materials. One example of my research is shown in the following paper:
https://www.sciencedirect.com/science/article/abs/pii/S1359645419301454?via%3Dihub |
| AZ |
| | Metron Aviation, Inc. | Dr. Rafal Kicinger | |
Large Business
|
Other Energy Technologies
| We provide extensive experience in developing representation spaces for conceptual and detailed design and machine learning capabilities for exploring these spaces aimed at generating novel design concepts. Our expertise includes knowledge acquisition techniques to develop parameterized and generative representations of complex engineering systems as well as application of population-based metaheuristic techniques (e.g., evolutionary algorithms, memetic algorithms, coevolutionary algorithms) operating on these representation spaces. We also offer capabilities for multi-objective optimization of design concepts and detailed designs supporting identification of Pareto frontiers and trade-offs among design objectives.
We also provide unique experience in the area of engineering applications of machine learning, particularly related to the rough sets-based inductive learning, conceptual designing, and engineering knowledge acquisition. Our existing practical applications include conceptual design in structural and transportation engineering domains. We have also developed expertise in constructive induction for conceptual design knowledge acquisition as well as know-how in implementing machine learning approaches for a large spectrum of engineering applications. In particular, one of our team members developed a methodological foundation, called Learning Engineering, encompassing engineering knowledge acquisition in a multistage learning process, quality assessment of the acquired knowledge in the context of its predictive power measured by a system of empirical error rates, and performance analysis of various learning systems.
Our team is interested in several areas of machine learning engineering research. First, we can develop a conceptual, methodological, and computational foundation to build a class of learning systems for engineering designing with an emphasis on inventive conceptual design. Second, we design and implement such systems specialized for the energy engineering applications. Third, we are also interested in the continuation of development of the Learning Engineering. Our research will be continuation of more than 35 years of our previous work in this area.
Current or prospective partners include:
• Dr. Tomasz Arciszewski, Co-I, Expert in machine learning in designing and engineering knowledge acquisition)
• Dr. Wojciech Ziarko, Expert in rough sets-based machine learning and development of learning algorithms
• Dr. Kalu Uduma, |
| VA |
| | ALEX - Alternative Experts Inc. | Robert Strickland | |
Small Business
|
Other Energy Technologies
| Velocity is ALEX - Alternative Experts’ (ALEX) Artificial Intelligence (AI) solution: a suite of capabilities designed to
support your organization and/or program to effectively gather, organize, analyze, and display data to meet your
mission-critical needs. Velocity empowers you to efficiently bring data together from disparate sources and turn
that information into organizational knowledge to support decision making in a fraction of the time of traditional
analysis.
Velocity’s state-of-the-art AI analytics technologies (processing models, analytical tools, and data management
capabilities) are based on open source software. Velocity rapidly combines AI capabilities to meet your analysis
and decision making needs with the most relevant, timely and comprehensive information and provides contextual
meaning to relate disparate data contained in structured and unstructured data formats.
Capabilities include:
• Data Acquisition – Continually aggregates disparate dynamic data sources and converts many data formats
(pdf, html, Microsoft products, etc.) into a common format for further analysis. Velocity also provides an audit
trail back to data sources.
• Entity Recognition and Relationship Mapping – Automatically identifies, extracts and organizes target data
for analysis and visualization, while maintaining linkages to source documents.
• v-Search Concept Search – Delivers an automated information retrieval method which searches electronically
stored structured and unstructured text for information that is conceptually similar to your search query.
Overcomes limitations imposed by classical Boolean keyword searches (false positives and false negatives
associated with synonymy and polysemy).
• v-Ask Models – You ask questions to extract information from an ingested dataset. V-Ask automatically takes
you to the specific locations in the documents where highly relevant results reside.
• Data Analytics and Visualization – Velocity processes, analyzes and displays the exact information you need
to make timely, informed, fact-based decisions about your program.
Areas where Velocity can impact your program:
ALEX delivers flexible, cost-effective AI integration to meet your program needs and increase your ability to make
informed decisions. Velocity is available in a variety of configurations to match your requirements and budget. |
| VA |
| | Brookline Chemical Co-operation | David Levy | |
Small Business
|
Other Energy Technologies
| Revolutionary method,including eqippment technology and products to drastically reduce energy requirements in textile processing .The system replaces high energy consumption that requires burning large amounts of gas or oil that are used to create the heat necessary to fix colours on textile,Our system reqires less than 1 sec.exposure to a unique light source of modified ultra violet light by reducing the energy requirements by approximately 90%.Large amounts of oil or gas are saved as well as eliminating Carbon Dioxide,Carbon Monoxide and Carbon Patriculates immission to the atmosphere,therefore drastically reducing energy consumptions, cost and provides clean air. |
| MD |
| | Columbia University | Alexander Urban | |
Academic
|
Other Energy Technologies
| Assistant professor in chemical engineering and founding member of the Columbia Electrochemical Energy Center (CEEC, https://ceec.engineering.columbia.edu/). Many years of experience in the atomic-scale modeling of inorganic materials, especially materials for Li-ion batteries, with first principles methods and coarse-grained techniques. Current research focus lies on understanding and overcoming degradation in batteries, fuel cells, and other electrochemical energy storage and conversion devices. We use machine learning to accelerate and to bypass conventional modeling. We make extensive use of databases, for example, for the storage and analysis of data generated by automated (high-throughput) calculations. |
| NY |
| | Michigan State University | Kalyanmoy Deb | |
Academic
|
Building Efficiency
| My research interest in development and application of efficient machine learning based optimal design and knowledge extraction methodologies. I have proposed efficient multi-criterion optimization methodologies which are extremely popular (in public domain) and has been commercialized by entrepreneurs. I work very closely with industries in design optimization activities including robust and reliable design, surrogate-assisted design, dynamically changed system design, hierarchical (multi-level) system design, exa-scale design optimization involving millions to billions of integer variables, and others. My machine learning based design activities developed nonlinear decision trees and random forests for classifier and regressor identification using feature relationships separating good from bad designs, deep neural networks for classifying images and identifying objects, and multi-reward function based reinforcement learning for process optimization tasks. We are pursuing current industry projects in the area of Explainable and interpretable AI. |
| MI |
| | Kebotix, Inc. | Semion Saikin | |
Small Business
|
Other Energy Technologies
| Kebotix, Inc. develops an integrated autonomous platform (Self-Driving Lab) for the accelerated discovery of molecules with targeted properties. The company is a spin-off from the Aspuru-Guzik Lab at the Department of Chemistry and Chemical Biology, Harvard University. Our technology combines generative machine-learning models for prediction of molecules with specific properties, conventional physical models, and robotic synthesis. This AI/Robotics feedback loop accelerates the discovery of new materials by more efficiently processing complex data and making better decisions. The approach is generic as it benefits a broad range of applications including materials for renewable and sustainable energy, energy storage, and energy efficient buildings. |
| MA |
| | University of Vermont | Safwan Wshah | |
Academic
|
Other Energy Technologies
| Computer science Assistant Professor with broader expertise and interests in deep learning, reinforcement learning, machine learning for power grids, computer vision, data analytics, and image processing. Experience in applying machine learning techniques to generate Molecules hypothesis using generative adversarial networks (GAN’s).
Dr. Wshah and his students are capable and interested in applying machine learning technique to many of the addressed research problems in this FOA. Specifically, we are interested in any of the design challenge problem such as hypothesis generation for electrical circuits and/or Materials/Molecules. In addition to any of the Hypothesis Evaluation. |
| VT |
| | University of Iowa | Andrew Kusiak | |
Academic
|
Power Generation: Renewable
| Research in systems engineering, smart systems, modeling, machine learning, and optimization.
Experience in development of models, algorithms, and solutions applied in energy generation, energy management, manufacturing, innovation. |
| IA |
| | Carnegie Mellon University | Haibo Zhai | |
Academic
|
Power Generation and Energy Production: Liquid and Gaseous Fuels/Nuclear
| Dr. Zhai conducts systems research in carbon capture technology, including process simulation and techno-economic analysis. Dr. Zhai would like to combine computational systems research with machine learning to explore advanced materials (e.g. high-performance polymeric membranes) for CO2 separation, which will help to meet the U.S. DoE's proposed cost target of CO2 capture for new-generation carbon capture technology. I am looking for collaboration with material scientists and AI experts. |
| PA |
| | Wayne State University | Yanchao Liu | |
Academic
|
Transportation
| We have expertise in using optimization and machine learning techniques to solve complex planning, operation and decision making problems. Our experience include preventive/corrective AC optimal power flow problems with security constraints, stochastic optimization in infrastructure planning, data-driven analysis and pricing of renewable generation resources, smart meter data mining and customer analytics.
Expertise include: Mathematical programming and optimization algorithms development using GAMS, R and Python.
We are a participant in the Grid Optimization Challenge organized by ARPA-E.
Our research has been published in IEEE Transactions in Power Systems, Energy Policy, The Electricity Journal, Transportation Science, Optimization Methods and Software, etc. |
| MI |
| | Pandata Tech Inc | Gustavo Sanchez | |
Small Business
|
Other Energy Technologies
| Pandata Tech is a Houston-based data analytics company that specializes in data quality solutions for the energy industry. We've developed a data quality platform that uses machine learning (ML) and artificial intelligence (AI) to make digital maintenance, optimization, and automation more reliable.
Companies have invested millions in data acquisition and streaming. This creates data chaos and historians. Millions of data point over thousands of signals need to be validated to make sure any future modeling and work returns benefit. Our machine learning tags, validates, and characterizes all this data at scale, allowing to bridge the real world with the digital world for better processes.
Our solution reduces false positives, false negatives, and time spent cleaning and validating data. Pandata's data quality checks reduce the amount of time it takes to clean data by at least 50%. This translates into data driven solutions that are cost saving, increase productivity, and increase team collaboration. Our data quality checks attribute to:
▸ decreasing downtime by 25% ▸ decreasing maintenance by 35% Pandata's data quality platform serves companies that include O&G exploration and production, power generation, IIoT, aerospace, and logistics.
These companies typically: ▸ process thousands of signals ▸ use digital maintenance / optimization / automation ▸ have pressure from operators to be digital ▸ have pressure to meet ISO reporting standards |
| TX |
| | University of South Carolina | Jochen Lauterbach | |
Academic
|
Other Energy Technologies
| High-throughput screening in combination with machine learning and statistical methods for discovery and optimization of novel catalysts. Knowledge extraction from experimental datasets. Rapid spectroscopic screening. |
| SC |
| | Imagars LLC | Baldur Steingrimsson | |
Small Business
|
Other Energy Technologies
| Imagars LLC provides engineering design software and services aimed primarily at mechanical design. Our patented Ecosystem is being used by mechanical engineering (ME) student design teams, in the US and Korea, both capstone, Formula and BAJA SAE teams. To companies in the automotive or aerospace industry, we offer software for requirement assessment and tracking, along with R&D services. In Phase II of our Small Business Innovative Research project with the National Science Foundation, we are developing a generic design framework capable of automatic verification of structured engineering requirements as well as improving design decision fidelity through application of big data analytics to repositories of known, good designs. The team behind Imagars consists of ME faculties from Portland State University, also with significant industry experience. Our distinguished software architect is a doctor from University of Minnesota with several awards from Intel for engineering excellence. |
| OR |
| Loading… |
|