afit afit - Academia.edu (original) (raw)

Papers by afit afit

A biologically inspired tactile sensor, the AFIT Neural Tactile Sensor (NTS), is proposed and exp... more A biologically inspired tactile sensor, the AFIT Neural Tactile Sensor (NTS), is proposed and experimentally evaluated. Incorporating ANN pattern recognition techniques, the NTS offers previously unattainable benefits in sensor size, simplicity, flexibility, sensitivity, and utility.

On September 18, 1997, Honeywell Technology Center (HTC) successfully completed a three-week flig... more On September 18, 1997, Honeywell Technology Center (HTC) successfully completed a three-week flight test of its rotor acoustic monitoring system (RAMS) at Patuxent River Flight Test Center. This flight test was the culmination of an ambitious 38-month proof-of-concept effort directed at demonstrating the feasibility of detecting crack propagation in helicopter rotor components. The program was funded as part of the U.S. Navy's Air Vehicle Diagnostic Systems (AVDS) program. Reductions in Navy maintenance budgets and available personnel have dictated the need to transition from time-based to 'condition-based' maintenance. Achieving this will require new enabling diagnostic technologies. The application of acoustic emission for the early detection of helicopter rotor head dynamic component faults has proven the feasibility of the technology. The flight-test results demonstrated that stress-wave acoustic emission technology can detect signals equivalent to small fatigue cracks in rotor head components and can do so across the rotating articulated rotor head joints and in the presence of other background acoustic noise generated during flight operation. During the RAMS flight test, 12 test flights were flown from which 25 Gbyte of digital acoustic data and about 15 hours of analog flight data recorder (FDR) data were collected from the eight on-rotor acoustic sensors. The focus of this paper is to describe the CH-46 flight-test configuration and present design details about a new innovative machinery diagnostic technology called acoustic fault injection. This technology involves the injection of acoustic sound into machinery to assess health and characterize operational status. The paper will also address the development of the Acoustic Fault Injection Tool (AFIT), which was successfully demonstrated during the CH-46 flight tests.

The authors provide a summary of recent research at the Air Force Institute of Technology (AFIT) ... more The authors provide a summary of recent research at the Air Force Institute of Technology (AFIT) in the area of neural networks. Specifically, AFIT research in the areas of error drive learning algorithm acceleration, speech recognition, target classification, time series prediction, and optical and VLSI implementations is presented. AFIT has developed and tested an algorithm which fits a curve to the error surface of a backpropagation surface to find more quickly a good set of weights. AFIT has investigated the use of momentum and second-order error-driven learning algorithms. A speech recognition system was developed using a combination of Kohonen nets and dynamic time warping. In the area of target classification, the accelerated backpropagation nets have been successfully applied. Research into predicting chaotic time series was performed. Three optical neural network architectures were designed and tested, and a VLSI implementation was investigated

A brief summary of the research at the Air Force Institute of Technology (AFIT) in the area of th... more A brief summary of the research at the Air Force Institute of Technology (AFIT) in the area of the neural networks is presented. AFIT has been investigating neural networks for military applications. During 1989, the research group consisted of approximately twenty people. Some of the work from this group is discussed. AFIT research into the areas of backpropagation relations to conventional algorithms, feature selection, neural networks for segmentation or general purpose preprocessing, angle-of-arrival detection, speech recognition, optical neural networks, and brain implants are presented

The purpose of this study was to begin development of an Inverse Synthetic Aperature Radar imagin... more The purpose of this study was to begin development of an Inverse Synthetic Aperature Radar imaging capability for the AFIT anechoic chamber. This began with an evaluation of the capabilities and limitations of the existing radar system and the chamber itself for this application. Then, after deciding on the image processing approach, software had to be written to collect the data necessary for image processing. This constituted the majority of this study, and resulted in a versatile, user-friendly program that automates the process of collecting data for high-resolution radar images. The program checks that the data to be collected will lead to a valid radar cross-section (RCS) image, but will allow data collection for general radar images. Finally, the image processing software was begun. This made use of commercially available software packages called PC-MATLAB and PRO-MATLAB. Further work is needed on the image processing software to generate calibrated images, and to perform focusing.

The Air Force Institute of Technology (AFIT) hosted a workshop on the Role of Wavelets in Signal ... more The Air Force Institute of Technology (AFIT) hosted a workshop on the Role of Wavelets in Signal Processing Applications on 12-13 Mar. 1992 at the AFIT Science and Research Center, Wright-Patterson AFB, OH. The workshop was sponsored by the Air Force Office of Scientific Research (AFOSR), Bolling AFB, DC. The major technical themes were as follows: (1) time/scale analysis versus frequency analysis of signals; and (2) filter bank structures versus discrete wavelet expansions.