| NSF Org: |
CMMI Division of Civil, Mechanical, and Manufacturing Innovation |
| Recipient: |
|
| Initial Amendment Date: | August 21, 2018 |
| Latest Amendment Date: | August 21, 2018 |
| Award Number: | 1839733 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Harry Dankowicz
CMMI Division of Civil, Mechanical, and Manufacturing Innovation ENG Directorate for Engineering |
| Start Date: | September 1, 2018 |
| End Date: | August 31, 2022 (Estimated) |
| Total Intended Award Amount: | $299,941.00 |
| Total Awarded Amount to Date: | $299,941.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
800 WEST CAMPBELL RD. RICHARDSON TX US 75080-3021 (972)883-2313 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
TX US 75080-3021 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | Special Initiatives |
| Primary Program Source: |
|
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.041 |
ABSTRACT
In recent years, there have been significant advances in machine learning - statistical techniques that enable computers to "learn" using available data. Machine learning methods have demonstrated great success in image recognition, language translation, speech processing, and other consumer applications. This has led to great interest globally in academia, industry, and government. The drawback in purely machine learning methods is that it does not use the knowledge of physical properties of specific system which could significantly improve the performance of these methods. This EArly-concept Grant for Exploratory Research (EAGER) project will lead to fundamental results and methods that combine the advantages of machine learning techniques and knowledge of physical attributes of the system to enable decision making and control of complex engineered systems. The research will be conducted in the context of control of large wind energy plants. Maximizing power production despite variable and uncertain operating conditions in large wind plants is an unsolved problem that is ripe for transformative approaches and innovation. The research from this project is likely to transition to industry by leveraging connections with the NSF I-UCRC for Wind Energy Science, Research and Technology (WindSTAR) as wind plant owners and operators constantly seek new ways to improve annual energy production and reduce the cost of electricity from wind.
The main idea of this EAGER project is to leverage advances in deep learning and high performance computing simulations for the control of complex engineered systems. Our hypothesis is that techniques from (semi-supervised) machine learning can be tailored to extract information from high performance simulation data to deal with the joint problem of identifying control system architectures and control algorithms for real-time decision making in complex engineered systems. The research goals of this project have great potential to contribute to the convergence of high performance computing simulations and data, machine learning, and controls to advance the state-of-art tools for controlling complex engineered systems. The testbed for the project is a wind plant. As turbines become larger, and are placed closer to one another, the aerodynamic coupling amongst turbines will increase resulting in a truly large-scale complex engineered system that must perform despite environmental uncertainty and variability of turbine components. Specific goals of this project include: Advanced learning algorithms for extracting control system architecture and training algorithms from large eddy simulation data of the wind farms; Real-time decision algorithms to select architecture and algorithms from site-specific libraries discovered in the first goal; and Real-time algorithms for tuning key parameters of the control solutions for additional improvements in the overall energy production.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
Complex engineered systems such as the power grid, air traffic control, transportation networks require coordination of many sensors and actuators to operate. The operation of these systems is accomplished by a combination of humans and computer systems to act on the sensor information for decision making and control. The architecture of the communication network (e.g., who talks to who?) and the architecture of the control layer (e.g., what actuators to command?) must be defined to operate these systems. This architecture can change with time. This exploratory project attempts to develop methods to extract information from large data sets to determine control system architectures and algorithms for the real-time control of complex engineered systems.
This project, while aiming for generally useful fundamental systems engineering research, is conducted in the context of control of large arrays of wind turbines. The data sets used for this project are obtained from high-fidelity computer simulations of wind farms. These computer simulations produce data generally available in a modern Supervisory Control and Data Acquisition (SCADA) system of a typical wind farm. The use of SCADA data to inform the research enhances the impact of the work in the wind energy community.
An outcome of the project is an algorithm that uses the power output of each turbine to decide which turbines (cluster) should coordinate their operation (control) to maximize the total wind farm power output. As the wind changes direction, the clusters of turbines may vary within the wind farm. The algorithm developed in this project is based on the correlation in time of the power production between turbines. The algorithm identifies and tracks the clusters whose power should be optimized to maximize the total farm power. This approach is quite practical because it is based on power signals readily available to the SCADA system and requires minimal communication between turbines. Due to its practicality, a patent application has been filed: "System and Method for Effective Real-Time Control of Wind Turbines (2022)," U.S. Patent Application No. 17/808,700.
Cluster identification accuracy could be improved with knowledge of changes on the prevailing wind direction into the wind farm. Neural networks (NNs) are developed to estimate the prevailing wind direction from the distribution of the wind turbine rotor angular speeds, which are also readily available from SCADA data. The use of these NNs in combination with the correlation-based clustering method is a first step toward a solution to the problem of decomposing a complex dynamic optimization problem into simpler subproblems in a wind energy application.
This project has trained three graduate students on advanced topics in signal processing, neural networks and wind energy. Two of these graduate students have joined industry, in part, due to skills acquired through this project. Other project outcomes include two archival journal papers, presentations at international conferences and poster presentations: including participation in the Ph.D. seminar of the European Academy of Wind Energy: https://www.eawe.eu/. This project is one of several projects executed at the University of Texas at Dallas Center for Wind Energy: https://wind.utdallas.edu/, whose mission is to conduct research and education to increase the electricity produced from wind in the Nation.
Last Modified: 02/02/2023
Modified by: Mario A Rotea
Please report errors in award information by writing to: awardsearch@nsf.gov.
