Award Data

An approach to object identification and sensor fusion of images is proposed. Preprocessing techniques which perform a useful and computationally efficient transformation on the image will be considered. Once the image has been transformed to a more efficient format, mathematical morphology and neural networks are proposed to address the issues of edge detection, identification, sensor fusion and ...

We will use an innovative neural network algorithm to perdict and control National Aero-Space Plane(NASP) unstarts at the earliest possible moment. Unstarts present a design challenge to hypersonic aircraft. An unstart occurs when the pressure at the aft end of the engine flow path reaches a critical level. This overpressure causes a "choking" of the air flow. The flow tends to spill around the in ...

During Phase I we will advance and develop innovative Adaptive Critic based neural network control methodologies specifically for a Remotely Piloted Vehicle (RPV) based upon the aerodynamics of the National AeroSpace Plane (NASP). Phase II will involve the actual implementation which will prove these neurocontrol concepts. This work will be the first step in creating the complex aerocontroller for ...

We will design a flowpath and a neural network based propulsion system controller for LoFlyte I, a remotely piloted vehicle (RPV) based upon the aerodynamics of the National AeroSpace Plane (NASP). This work will be the first step to a highly innovative RAM/SCRAM propulsion system and to a propulsion controller for the ultimate aircraft in the LoFlyte Unmanned Autonomous Vehicle (UAV) program seri ...

The purpose of this proposal is to develop a new generation of "SMART" neurocontrol actuator systems for use on hypersonic aircraft. Develop a testbed to see that the actuator system will work. This will also optimize and scale the testbed vehicle sizing. This concept using adaptive neural network technology will improve performance and behavior for hypersonic aircraft like the National AeroSpace ...

The manufacture of composite materials for use as high confidence components in aircraft has resulted in a requirement for rigorous defect analysis. This proposal researches the use of neural network technology combined with Laser Ultrasonics to provide the quality assurance inspector with the capability of identifying potential defects in composite structures. Neural network technology is used to ...

N/A

N/A

We propose the exploration of single crystal GaN waveguides for the fabrication of optoelectronic integrated circuits. The feasibility of using GaN for short wavelength (up to 365 nm) OEIC's will be established in Phase I via the demonstration of a channel waveguide based phase shifter. The Al(sub x)GA(sub 1-x)N material system with its transparency from 365 nm to 12 microns, tunable refractive in ...

The current development of an electric power generation system for the More Electric Aircraft (MEA) is based on a low-risk extension of existing three-phase, switched reluctance machine (SRM) technology. This research program proposes to study an alternate two-phase SRM and its associated power-conditioning converter. By the nature of the proposed machine, it has 50% of its stator coils active at ...