Nicholas Goodman

Advanced Time–Frequency Mutual Information Measures for Condition-Based Maintenance of Helicopter Drivetrains

A new concept of nonparametric signal detection and classification technique is proposed using mutual information measures in the time-frequency domain. The time-frequency-based self-information and mutual information are defined in terms of the cross time-frequency distribution. Based on time-frequency mutual information theory, this paper presents applications of the proposed technique to real-world vibration data obtained from a dedicated condition-based-maintenance experimental test bed. Baseline, unbalanced, and misaligned experimental settings of helicopter drivetrain bearings and shafts are quantitatively distinguished by the proposed techniques. With imbalance quantifiable by variance in the in-phase mutual information and misalignment quantifiable by variance in the quadrature mutual information developed and presented herein, machine health classification can be accomplished by use of statistical bounding regions.

Applications of time-frequency analysis for aging aircraft component diagnostics and prognostics

The classical time-frequency distributions represent time- and frequency-localized energy. However, it is not an easy task to analyze multiple signals that have been simultaneously collected. In this paper, a new concept of non-parametric detection and classification of the signals is proposed using the mutual information measures in the time-frequency domain. The time-frequency-based self and mutual information is defined in terms of cross time-frequency distribution. Based on the time-frequency mutual information theory, this paper presents applications of the proposed technique to real-world vibration data. The baseline and misaligned experimental settings are quantitatively distinguished by the proposed technique.

Design of advanced time-frequency mutual information measures for aerospace diagnostics and prognostics

Accelerometer data has been gathered from accelerated conditioning in grease lubricated and lubrication deprived gear meshes in AH-64 helicopter intermediate and tail rotor gearbox, which are commonly problematic components of the Apache helicopter platform. These tests were performed in a controlled drive-train research test bed, simulating drive-train conditions to improve diagnostic and prognostic capabilities of Condition Based Maintenance (CBM) practices in Integrated Vehicle Health Monitoring System - Health Usage Monitoring System (IVHMS-HUMS) and other comparable CBM packages, as monitored by a standardized Digital Source Collector (DSC) system. Time-frequency representations of vibration measurement collected from two spaced sensors are used to provide signature analysis of transient system harmonics. Furthermore, the time-frequency mutual information advanced signal processing technique is then proposed and validated using vibration data. The measure advances the development of mutual information health indicators to quantify degradation of the helicopter power train. The AH-64 test systems perform under stress in realistic loading conditions and lifetime accelerated aircraft aging is monitored using the proposed advanced signal processing techniques for baseline tests for comparison with faulted conditions.1 2

Information extraction from helicopter maintenance records as a springboard for the future of maintenance text analysis

This paper introduces a novel application of information extraction techniques to extract data from helicopter maintenance records to populate a database. The goals of the research are to preprocess the text-based data for further use in data mining efforts and to develop a system to provide a rough analysis of generic maintenance records to facilitate in the development of training corpora for use in machine-learning for more refined information extraction system design. The Natural Language Toolkit was used to implement partial parsing of text by way of hierarchical chunking of the text. The system was targeted towards inspection descriptions and succeeded in extracting the inspection code, description of the part/action, and date/time information with 80.7% recall and 89.9% precision.