Teaming Partners

Submit Entry to Teaming Partner List
v
   Show Advanced Search
Keyword Search includes Investigator Name, Organization, Background, and Address. Use operators "AND" or "OR" to fine tune your search. Please use only one operator per search. For example, the search term "biofuels AND modeling" will return results that include both the words biofuels and modeling, while the search term "biofuels OR modeling" will return results that include the word biofuels, modeling, or both.
View Archived Teaming Partners

By enabling and publishing the Teaming Partner List, ARPA-E is not endorsing, sponsoring, or otherwise evaluating the qualifications of the individuals and organizations that are self-identifying themselves for placement on this Teaming Partner List.

The columns below can be sorted alphabetically by clicking on the column heading and reverse alphabetically sorted by clicking twice on the column heading. Type into the white boxes or use the dropdown options to filter within the search results.

 
Organization 
Investigator Name 
Organization Type 
Area of Expertise 
Background, Interest,
and Capabilities
 
Contact Information 
State 
 
xv
xv
 
xv
 Cornell UniversityLang Tong Academic Grid Background:
machine learning---statistical inference, deep learning neural networks, reinforcement learning, signal processing
Optimization---stochastic and dynamic optimization. Markov decision processes.

Interest:
Applying AI, machine learning, and data analytic tools in energy and power systems, large scale charging of electric vehicles, and smart grids.

Capabilities:
-Online learning techniques for probabilistic forecasting of power systems and market operations.
-Deep learning and data-driven approaches in wide-area situation awareness: state estimation, online stability assessment, and quickest detection of voltage instability.
Website: http://people.ece.cornell.edu/ltong/

Email: lt35@cornell.edu

Phone: 6072553900

Address: ECE, Cornell University, ithaca, NY, 14853, United States
NY
 IPS, Inc.Chris Franz Small Business Other Energy Technologies Secure Cloud Transitions
IPS and our commercial division, To t e m , have developed private, hybrid and public cloud architectures for customers ranging from the US Government to private Financial Technology companies. These systems provide scalability, cost efficiency and future readiness with security ranging from SEC/FINRA financial data to air-gap privacy at the top level. We help transition legacy architectures and applications into sustainable systems with a lower TCO.

Data Dominance
Data is the fuel source for business. Being able to organize what you have, collect what you want and stage the data for use is what
keeps you ahead. We prefer to layer data technologies to get you the best performance for the least risk. We use machine learning, blockchain,
tensors and artificial intelligence to get the most out of your data and ensure security. We turn data into decisions.

Custom Systems Engineering
We like the tough problems. From developing the first HD digital night vision system to architecting billion dollar satellite constellations, we pride ourselves on leveraging our expertise and the latest technology to make our customers more productive and profitable.

We specialize in enabling your company to flex with the ever-changing design or contractual requirements through Teaming and Subcontractor agreements.
Website: www.intelpayloads.com

Email: chris@intelpayloads.com

Phone: 7193517020

Address: 4010 Hidden Rock Rd, Colorado Springs, CO, 80908, United States
CO
 University of South CarolinaJianjun Hu Academic Other Energy Technologies Dr. Hu's research interests are in the area of machine learning, deep learning, data mining, big data, evolutionary computation and their applications in material informatics, bioinformatics and health informatics. Currently, his major research focus is developing deep learning algorithms for solving challenging application problems such as: intelligent audio/sound processing, data-driven material discovery, medical image analysis, genomics based disease gene discovery, protein-peptide binding prediction for drug design and protein design, big data driven analytics for prevention of HIVs, fault diagnosis and text mining. His research has been sponsored by NSF, NIH, Nvidia and Department of Transportation of South Carolina.

Interests: deep learning, machine learning, big data, and materials informatics

Capability: data driven predictive modeling, deep learning models for materials property prediction and screening, global optimization via genetic algorithm, open-ended design using genetic programming, bioinformatics.
Website: https://cse.sc.edu/~jianjunh/

Email: jianjunh@cse.sc.edu

Phone: 8037777304

Address: 550 Assembly Street, Storey Innov. Center, Columbia, SC, 29201, United States
SC
 The University of UtahPania Newell Academic Power Generation and Energy Production: Fossil/Nuclear I have several years of experience working at DOE labs before starting my academic position. I have led several DOE projects through different offices such as Office of Basic Sciences and Fossil Energy. I am currently a PI on an EFRCs (MUSE).

My research interest lies at the intersect of theoretical, numerical, and experimental study of porous media. Topic such as:

• Multi-physics modeling and experimental study of porous media
• Computational modeling of fracture in porous media
• Multi-scale modeling of heterogenous porous systems
• Homogenization methods
• Physics-based machine learning techniques


Capabilities:
• State-of-the-art nano-fab user facility
• Physics-based modeling tools
Website: https://newell.mech.utah.edu

Email: pania.newell@utah.edu

Phone: 801-213-3635

Address: 1495 East 100 South, Salt Lake City, UT, 84112, United States
UT
 CrossnoKayeThomas Foley Small Business Other Energy Technologies CrossnoKaye was founded in 2017 by two Harvard applied physics Ph.D.s, soon joined by another physics Ph.D. in early 2018. As it's grown, CrossnoKaye's combined backgrounds and experiences now span a vast range of subjects. We are broadly interested in controls & automation, energy, and optimization. They develop and deploy high-level (control) strategies for industrial automation, with an emphasis on using bottom-up, physics-based modeling to inform and implement the strategies.

Our capabilities and expertise include:
-Thermodynamics and statistical mechanics
-Numerical optimization, including stochastic methods and convex
-Bayesian inference and statistics
-Physics-based modeling
-Simulation
-Controls theory and automation
-Machine learning
-Software development, from cloud-based optimization to PLCs
-Energy markets
-Industrial refrigeration
-Water treatment

CrossnoKaye creates and deploys high-level control strategies for large industrial facilities while employing modern software engineering practices and state-of-the-art modeling, inference, and machine learning techniques. By employing facility-level, energy-centric, and physics-based models of processes and their electricity usage, CrossnoKaye can transform facilities into on-demand virtual batteries and load-balancing assets. This transformation of energy-intensive industrial facilities helps balance the grid and improves system energy efficiency, all while saving operators money.

Through their partnership with Lineage Logistics, the largest cold storage company in the world, they conceived, developed, and deployed a strategy named 'thermal flywheeling’. Thermal flywheeling treats the contents of a facility as a large thermal battery, with the ability to ‘charge’ by over-cooling when electricity is cheap and ‘discharging’ (reducing electricity usage) when electricity is more expensive. By load-shifting in this manner, such facilities not only save operators’ money on energy spend but also help California overcome the so-called ‘duck-curve’ problem, which has otherwise hindered the adoption of renewables.
Website: www.crossnokaye.com

Email: foley@crossnokaye.com

Phone: 5306323028

Address: 1129 State Street, Suite 1, Santa Barbara, CA, 93101, United States
CA
 Hitachi America LTDBo Yang Large Business Grid Background: new product development in the area of T&D, renewable integration, distribution planning and operation

Interests: work with AI experts and data scientist to explore new solutions boosting model based grid analysis

Capabilities: We have a team with energy modeling, data analytics and software development capabilities
Website: http://www.hitachi-america.us/rd/#research-areas

Email: bo.yang@hal.hitachi.com

Phone: 6692619318

Address: 2535 Augustine Dr. 3rd floor, Santa Clara, CA, 95054, United States
CA
 Vishwamitra Research InstituteUrmila Diwekar Non-Profit Power Generation and Energy Production: Fossil/Nuclear We work in the area of optimization under uncertainty with applications to fossil, nuclear power systems as well as renewable energy systems like solar and bioenenrgy. We have capability to model, optimize, and control of these systems in the face of uncertainties.
Website: www.vri-custom.org

Email: urmila@vri-custom.org

Phone: 6308863047

Address: 2714 Crystal Way, Crystal Lake, Crystal Lake, IL, 60012, United States
IL
 analog photonicsEhsan Hosseini Small Business Other Energy Technologies Analog Photonics developed proprietary and patented integrated photonics technology on a CMOS-compatible 12” integrated photonics platform. Using a combination of silicon and silicon nitride as core waveguide layers our silicon photonics platform is low loss and can handle high optical power in the visible and near-infrared region of the electromagnetic spectrum. Having the capability to achieve both high, medium and low index contrast is at the basis of our state-of-the-art photonic components while maintaining a low footprint. The large temperature dependent refractive index of silicon enables highly efficient thermal tuning while the low temperature dependent refractive of silicon nitride enables temperature independent operation.
Website: www.analogphotonics.com

Email: ehsan@analogphotonics.com

Phone: 4042909198

Address: suite 205, Boston, MA, 02210, United States
MA
 DiakontTyler Powell Small Business Other Energy Technologies We specialize in robotic non-destructive examination (NDE) of pipelines and oil & gas storage tanks. We would like to use machine learning to reduce the amount of time required to analyze data and provide asset status information to the operators in a more timely manner. Our goal is to provide full reports to asset owners within 24 hours of completing the inspection (currently 30-60 days).

As part of our inspections, we collect large amounts of ultrasonic (UT) and electromagnetic acoustic (EMAT) data, then analyze it to determine metal thickness. We would like to use machine learning to correctly process the A-scan to measure the coating & metal thicknesses and then identify, classify & measure defects.
Website: http://www.diakont.com/energy_services/home.html

Email: tpowell@diakont.us.com

Phone: 8585515551

Address: 3193 Lionshead Ave, Carlsbad, CA, 92010, United States
CA
 Michigan State UniversityJohn R. Dorgan Academic Bioenergy Broad expertise from 25 years of experience with biorefining issues. Former Site Director of the Colorado Center for Biorefining and Biofuels (C2B2), a consortium of three State Universities an the NREL DOE Lab. Knowledgeable in polymer membrane based separations.

Specialized deep expertise in polymer materials science with an emphasis on bioderived polymers and resins. Have developed renewable resin systems suited for manufacturing wind turbines. Active in IACMI and REMADE NNMIs.

Developed and maintained suite of molecular simulation codes for polymer materials discovery that are orders of magnitude faster than traditional MD methods. Interested in combining these codes with machine learning algorithms to design new biobased polymers, lubricants, and surfactants.
Website: https://scholar.google.com/citations?user=NRl0mY0AAAAJ&hl=en

Email: jd@msu.edu

Phone: 3039565767

Address: 428 S. Shaw Lane, East Lansing, MI, 48824, United States
MI
 San Diego State UniversityChris Mi Academic Transportation Has extensive experience in electric vehicle technology, including powertrain optimization, electric machines, power electronics, wireless charging, battery management.

Have taken on three ARPA_e projects and multiple EERE projects including the GATE center.
Website: chrismi.sdsu.edu

Email: mi@ieee.org

Phone: 7347658321

Address: 5500 Campanile Drive, E-426, San Diego, CA, 92130, United States
CA
 EnPower, Inc.Adrian Yao Small Business Other Energy Technologies EnPower is developing next-generation Li-ion cells featuring advanced electrode architectures that enable significantly faster charging speeds, longer cycle life, and safety. EnPower has setup a pilot manufacturing and R&D facility in Phoenix, AZ capable of producing large capacity pouch cells from powder to product. EnPower is also integrating its cell technologies into advanced battery pack systems for various application industries, and has started using machine learning techniques for the optimization of real-cell performance in charge, discharge, and SOC estimation.
Website: www.enpowerinc.com

Email: adrian@enpowerinc.com

Phone: 8326933570

Address: 777 W Pinnacle Peak Rd. Ste B-109, Phoenix, AZ, 85027, United States
AZ
 U.C. BerkeleyAvideh Zakhor Academic Building Efficiency * Faculty member in EECS at UC Berkeley with expertise in machine learning
* Have led multiple ARPA-E projects in use of machine learning in building energy efficiency.
Website: www-video.eecs.berkeley.edu

Email: avz@berkeley.edu

Phone: 5103843272

Address: University Of California, Berkeley, CA, 94720-0001, United States
CA
 Kansas State UniversityChuancheng Duan Academic Power Generation: Renewable Keywords: Fuel cell, electrolyzer, materials design and evaluation.

Dr. Duan is an Assitant Professor at Kansas State University. His research focuses on fuel cells, electrolyzers, reversible fuel cells. His previous work on fuel cells and electrolyzers has been published in Nature, Science, and Nature Energy. He is emerging as the international/national leader in the field of intermediate-temperature protonic ceramic fuel cells (PCFCs) and protonic ceramic electrolysis cells (PCECs).

Expertise in materials design, fabrication, and characterizaiton.
Expertise in fuel cells, electrolyzers, and reversible fuel cells.

5+ years of experience of working on ARPA-E projects (REBELS and REFUEL)
Website: https://sites.google.com/view/cduan

Email: cduan@ksu.edu

Phone: 720-648-7886

Address: 1701A Platt St, Manhattan, KS, 66506, United States
KS
 Lehigh UniversityCarlos Romero Academic Power Generation and Energy Production: Fossil/Nuclear Background
This teaming partner input is on behalf of the Thermal Energy Storage Team at Lehigh University. Our team has worked on thermal energy storage projects that include sensible, latent and thermochemical energy storage research. Some of these projects involve different media, such as encapsulated phase change materials, molten salts, enhanced concrete and metal oxides for REDOX reversible reactions. Projects also include a range of temperatures and applications, from 35 deg. C (for supplemental cooling of air-cooled condensers) to 1,000 deg. C (for concentrating solar power). The team has also participated in projects that involve data analytics, machine learning, materials design and artificial intelligence and optimization, in the context of thermal energy systems and power generation plants.

Interest
Our interests for this ARPA-E announcement is in the particular area of enhancing research results and designs of thermal energy storage systems through machine learning. Thermal energy storage inherently conjugates very complicated processes involving materials, heat and mass transfer, fluid mechanics, and chemical kinetics. Machine learning would offer a vehicle to optimize reactor and system designs which include a thermal energy storage medium. Interests lays on supervised (task driven) and unsupervised (data driven) machine learning approaches. This would facilitate rapid deployment of energy storage solutions to solar power applications and improvement in power generation flexibility of fossil-fired power plants.

Capabilities
Lehigh University has a vast array of laboratory capabilities related to thermal energy storage, which includes thermogravimetric analyzers, differential scanning calorimeters, bomb calorimeters, thermal kilns, ovens, radiant heat panels and furnace systems for thermal characterization, and universal testing machines for full-scale mechanical characterization. Lehigh University laboratory capabilities also include a range of analytical equipment that involves scanning electron microscopes, X-Ray diffraction, inductively coupled plasma mass spectrometers and atomic absorption spectrometers. Dedicated high-performance computing facilities are also available to support the data-intensive research activities.
Website: https://www1.lehigh.edu/research/interdisciplinary-research-institutes/cyber-physical-infrastructure-energy

Email: cerj@lehigh.edu

Phone: 6107584092

Address: 117 ATLSS Drive, Bethlehem, PA, 18015, United States
PA
 CogniTech CorporationMichael Salazar Small Business Other Energy Technologies Experience in software design and programming for chemical applications. Much experience in programming and using molecular dynamic simulations of system sizes ranging from 3 atom state-to-state processes to large reactive chemical systems. Experience is running many electronic structure codes. Experience in programming in many languages.
Website: http://cognitech-ut.com

Email: uuchemprof@gmail.com

Phone: 7316182227

Address: 4200 E Main St., Humboldt, TN, 38343, United States
TN
 Washington State UniversityAssefaw Gebremedhin Academic Grid Currently an assistant professor in the School of Electrical Engineering and Computer Science at Washington State University, where he directs the Scalable Algorithms for Data Science Lab (SCADS) (https://scads.eecs.wsu.edu/). Recipient of NSF CAREER Award (2016) for work on fast and scalable combinatorial algorithms for data analytics. Current research interests include: machine learning and data mining, network science, high performance computing, edge computing, and sequence analysis. His PhD student Helen Catanese recently won the National Academies of Science, Engineering and Medicine's Elevating Mathematics Video Competition featuring work on network science for sequence analysis (http://sites.nationalacademies.org/DEPS/BMSA/DEPS_190706).

Previously he served as a founding member and co-investigator in the Combinatorial Scientific Computing and Petascale Simulations (CSCAPES) Institute, a multi-institution project funded by the Department of Energy under the SciDAC-2 program.
Website: https://www.eecs.wsu.edu/~assefaw/

Email: assefaw.gebremedhin@wsu.edu

Phone: 509-335-3952

Address: EECS, Washington State University, Pullman, WA, 99164, United States
WA
 Hawaii Natural Energy Institute, University of HawaiiKevin Davies Academic Grid I have a multi-disciplinary engineering background (B.S. ECE from Carnegie Mellon and Ph.D. Mech E from Georgia Tech) with domain knowledge in physics-based modeling, embedded controls, data analytics and optimization, model-based systems engineering, and software/hardware/product development. My major work and research has been in the automotive industry (4 years at Ford including EVs, HEVs, and FCEVs), multi-domain object-oriented modeling of fuel cells and systems (6 dedicated years of experience in the Modelica language), and grid integration of renewable energy (4 years in this area at the Hawaii Natural Energy Institute, HNEI). I am currently at HNEI, which has focus areas in electrochemical devices and systems, alternative fuels, renewable energy generation, energy efficiency and transportation, and grid integration.

I would be interested in partnering with a machine learning expert on topics that involve:
- Real-time and/or distributed modeling for dynamic optimization, diagnostics, and controls
- Electric power systems, particularly distributed energy resources (DER), variable renewable energy (wind and solar), non-wires alternatives, and grid energy storage
- Disaggregation of load and PV data
- High-fidelity solar forecasting
- Edge computing and real-time data analytics
- Time-synchronized harmonic measurement for grid fault location
I have various levels of ongoing research, proposals, and collaborations in these areas.

I can contribute the following resources for research, development, and test:
- Real-time simulator with grid power hardware-in-the-loop capabilities (time steps down to 10 us, can run Simulink, Modelica, and/or phasor domain power flow models)
- Custom-developed grid power monitor with advanced capabilities including harmonic measurement, GPS synchronization, FPGA and CPU-based processing, low-latency pub/sub messaging, and multiple networking interfaces (WiFi, Ethernet, LTE, wireless mesh)
- Large data sets of distribution grid conditions under high penetrations of distributed PV -- several years of 1 s data of 34 transformers and 17 residences with rooftop PV (Maui)
- Detailed distribution grid models
- Physics-based models of fuel cells encompassing heat and mass transfer and electrochemistry

I have various connections to other labs and companies in the electric grid/renewable energy space that could be leveraged. In particular, we work closely on demo projects with utilities in Hawaii and beyond.
Website: https://www.linkedin.com/in/kevinldavies/

Email: kdavies@hawaii.edu

Phone: 8089563180

Address: 1680 East-West Rd, POST 109, Honolulu, HI, 96822, United States
HI
 AionicsAustin Sendek Large Business Other Energy Technologies Aionics provides a machine learning-based battery design platform providing value to R&D teams in fundamental materials design, cell design, and cell operation. Informed by millions of data points on materials and their properties, Aionics enables teams to extract deep scientific insights from their performance data, as well as use their performance data to inform screening of large databases of candidate materials and compositions. Aionics was spun out of Stanford University in 2018 by Dr. Austin Sendek and was featured in Forbes 30 Under 30 in Energy for 2019. Aionics is now accelerating research at many leading battery manufacturers and OEMs, ranging from young startups to Fortune 50 electronics companies.

Aionics provides capabilities in fundamental materials design and discovery, leveraging machine learning approaches developed at Stanford that have been shown to lead to increased rates of materials discovery over searches led by human intuition. For example, Aionics currently has multiple ongoing engagements in solid electrolyte discovery based around requirements in ionic conductivity, electrochemical stability and/or synthesizability, with these engagements leading to multiple patent applications for our customers. Aionics also provides capabilities in materials design and optimization around cell-level performance metrics including cycle life; current engagements include the optimization of liquid electrolytes and electrode additives for cycle life. Aionics also assists in smart battery deployment including data sharing across OEMs in order to manage battery health in order to minimize degradation.

"The Aionics platform has been an invaluable tool for helping our R&D team narrow in on the best materials in a fraction of the time." - Battery company CEO
Website: aionics.io

Email: austin@aionics.io

Phone: 5305982052

Address: 623 South Delaware St., San Mateo, CA, 94402, United States
CA
 Wayne State UniversityProfessor Golam Newaz Academic Power Generation: Renewable Professor Newaz has extensive experience with advanced materials, composites and layered dissimilar material assemblies. His expertise spans both micro and macro behavior of such assemblies and works on both experimental as well as computational fields. He is currently working on mechanistic issues related to Li-ion batteries e.g., external load induced deformation and onset on internal short circuit (ISC). His work is sponsored by Ford Motor Company. His group also focuses on computational simulation of creation of hot spots due to ISC and possible thermal runway using
thermal-fluid codes.

Professor Newaz is also working on vehicle to building (V2B) efforts with Next Energy, a non=profit entity next to Wayne State University.

The goal of this project is to develop predictive machine learning (ML) models for demand mitigation considering different vehicle to building (V2B) charge/discharge scenarios, grid power data and weather conditions. Also, ML methods will be used to identify the main factor that controls the demand and supply. Then multilinear regression models will be developed for user-friendly forecasting. Finally, active learning models will be developed for real-time forecasting. If successful, these models can be used for real-time decision making.

What can we do with existing dataset?

1. Machine learning-based forecasting models to predict short-term building energy supply and demand in ultra-small scales.
2. Advanced visualization schemes considering multiple variables.
3. Active learning models for real-time forecasting.

There is extensive materials research capabilities and excellent grid structure and data collection facilities at Next Energy for charging stations.
Website: https://engineering.wayne.edu/profile/ad5874

Email: gnewaz@eng.wayne.edu

Phone: 734.223.1006

Address: 5050 Anthony Wayne Dr, Detroit, MI, 48202, United States
MI
 Michigan State UniversityHui-Chia Yu Academic Other Energy Technologies Dr. Yu's expertise is to simulate detailed multi-physics materials phenomena at the microstructure scale. Specific subjects are electrochemical dynamics at battery and solid oxide fuel cell complex electrodes, micro-mechanics and crack propagations due to electrochemical-mechanical-thermal coupled effects during battery and fuel cell operations, and fluid mechanics coupled electrochemical reactions in complex electrodes. He uses simulations to predict electrochemical performance of electrodes and to guide microstructure design to improve electrode performance, as well material selections. His simulations also bridge multi-scale phenomena, connecting microstructural effects to macroscopic material properties. He is interested in combining physics-based detailed simulations with machine learning to accelerate electrode design and material selections.
Website: https://cmse.msu.edu/directory/faculty/hui-chia-yu/

Email: hcy@msu.edu

Phone: 5174320608

Address: 428 S Shaw Ln, East Lansing, MI, 48824, United States
MI
 Robert Bosch LLCGiovanna Bucci Large Business Power Generation: Renewable Research field of interest include:
- Mesoscale modeling of coupled electrochemical-mechanical systems
- Energy storage materials modeling
- Fracture mechanics
- Coarse grained modeling of polymers

I have basic knowledge of ML algorithms and experience in implementing ANNs in pytorch

The final deliverable of the project I would like to propose: optimal testing protocol for the selection of materials/components and to define operating regimes for extended durability of PEM-fuel cells
Website: http://web.mit.edu/bucci/www/index.html

Email: giovanna.bucci@us.bosch.com

Phone: 6178722891

Address: 384 Santa Trinita Ave, Sunnyvale, CA, 94085, United States
CA
 Argonne National LaboratoryKirill Prozument Government Owned and Operated (GOGO) Other Energy Technologies We have experimental capabilities in quantifying the products chemical reactions or static molecular samples in the gas phase. Chirped-pulse Fourier transform millimeter-wave spectroscopy is utilized to study the pyrolysis and photolysis chemistry. Recently, we demonstrated the potential of applying artificial neural networks to assign broadband rotational spectra and identify chemical species: J. Chem. Phys. 149, 104106, (2018). Further work and expertise in pattern recognition is needed to fully automate decoding of rotational spectra. We are also interested in applying machine learning to build and improve complex networks of gas-phase chemical reactions. In particular, we think that using graph neural networks and active learning may be the potentially fruitful direction. We have the expertise in theoretical chemistry, kinetic modeling and experimental verification of the chemical kinetics models.
Website: https://www.anl.gov/profile/kirill-prozument

Email: prozument@anl.gov

Phone: 630-252-7666

Address: 9700 S Cass Ave, Bldg 200, Lemont, IL, 60439, United States
IL
 Lawrence Berkeley National LaboratoryDonghun Kim Government Owned and Operated (GOGO) Building Efficiency Dr. Donghun Kim received his Ph.D. degree from Purdue University with focus on management of thermal energy systems. He has been worked as a research assistant professor at the School of Mechanical Engineering at Purdue University and currently work a research scientist at Lawrence Berkeley National Lab. His academic background includes system identification, control (model predictive control in particular) and optimization to develop, evaluate and deploy advanced building HVAC control algorithms. He developed an identification algorithm and model predictive controller to coordinate a multiple Rooftop unit, and algorithms for generating reduced order models for building envelope systems and dynamic vapor compression systems. He is a technical committee member of the American Society of Heating, Refrigerating, and Air-conditioning Engineers (ASHRAE), and of the American Society of Mechanical Engineers (ASME) Energy Systems, and a member of the Institute of Electrical and Electronics Engineers (IEEE).
Website: https://www.linkedin.com/in/donghun-kim-263b3437/

Email: donghunkim@lbl.gov

Phone: 7655866076

Address: 1 Cyclotron Rd, Berkeley, CA, 94720, United States
CA
 CogniTech CorporationJerome Soller Small Business Other Energy Technologies I received my BS in Electrical Engineering from the Johns Hopkins University and PhD in Computer Science from the University of Utah. As President and CEO of our small business, I manage a team of mostly PhD level scientists, engineers, and data scientists. I specialize in applied machine learning and other data sciences research. My expertise includes the application of machine learning, deep learning, data mining, and other analytics to applications in energy, healthcare, and defense. One of our areas of focus is classification, anomaly detection, and automated model selection for static and time series data. My team and I also have expertise in developing software implementations of specialized computational algorithms for both Hadoop Big Data environments and also Jupyter environments.
Website: www.cognitech-ut.com

Email: SOLLER@COGNITECH-UT.COM

Phone: 8013220101

Address: 1060 East 100 South Suite 306, Salt Lake City, UT, 84102, United States
UT
Page 1 of 3 (65 items)Prev[1]23Next