Grants and Contracts Details
Description
Turbines are widely used in the energy and transportation sectors, accounting for 15.7 quadrillion
BTUs of annual energy consumption. According the U.S. Energy Information Administration, this
figure represents 16.1% of the total energy consumed in the U.S., which is 43% larger than all
renewable energy within the current energy portfolio [1]. As a result, there is significant interest
in realizing even minute improvement in the efficiency of turbines, including platforms for power
generation as well as jet engines for transportation. OEM’s continue to invest significant
resources to improve performance with new metallic, ceramic and composite materials. These
novel materials, such as advanced nickel-based superalloys and ceramic matrix composites, are
capable of operating at increasingly higher temperatures, which allows for more efficient turbine
operation. However, while there have been tremendous advances in the Materials Science of
turbine materials, the Manufacturing Science necessary to efficiently process them has been
lacking.
Proposed New Technology, Target Performance and Potential Impact
We propose to leverage transformative advances in reinforcement learning, by using
computationally-efficient physics-based process modeling to enable continuous acquisition of
digital manufacturing expertise, in order to enable at least 10% reduction in the total life cycle
embodied energy of advanced turbine components. Our AI-Enabled Manufacturing approach will
enable more energy-efficient manufacturing and more effective use of difficult-to-process
turbine materials. Furthermore, the approach will improve functional performance
characteristics such as fatigue life and creep resistance through tailored mechanical treatments
on existing manufacturing equipment. By offering more efficient and reliable processing
strategies for industry, we expect more efficient turbine designs to become technically feasible
and cost-effective to manufacture. While current raw material shortages and insufficient digital
manufacturing tools are forcing turbine manufacturers to empirically adopt conservative (i.e. low
productivity) and inefficient (i.e., high energy consumption) processing strategies to limit
manufacturing scrap, our work will help identify more aggressive, yet reliable, strategies for
processing scarce high temperature alloys.
Status | Finished |
---|---|
Effective start/end date | 5/15/20 → 5/14/22 |
Funding
- Department of Energy: $497,685.00
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.