Detecting strain-gauge failures in stress-cycle count matrices

TY - GEN

T1 - Detecting strain-gauge failures in stress-cycle count matrices

AU - Hickinbotham, S J

AU - Austin, J

PY - 1999

Y1 - 1999

N2 - The structural health of airframes is often monitored by analysis of the frequency of occurrence matrix (FOOM) produced after each flight. Each cell in the matrix records a stress event of a particular severity. These matrices are used to determine how much of the aircraft's life has been used up in each flight. Unfortunately, the sensors that produce this data are subject to degradation themselves, resulting in corruption of FOOMs. This paper reports a method of automating detection of sensor faults. It is the only known method that is capable of detecting such faults. The method is in essence a pair of novelty detection algorithms that produce measures of unusual counts of stress events at the level of the individual cell and unusual distributions of counts over the entire FOOM. Cell-level error is detected using a probability threshold and a sum of standard deviations. FOOM-level error is detected using a novel application of the Eigenface algorithm of Turk and Pentland [1]. These measures are used as inputs to a multi-layer perceptron (MLP) that is trained to classify FOOMs as normal or corrupted. Classification success is generally over 95%.

AB - The structural health of airframes is often monitored by analysis of the frequency of occurrence matrix (FOOM) produced after each flight. Each cell in the matrix records a stress event of a particular severity. These matrices are used to determine how much of the aircraft's life has been used up in each flight. Unfortunately, the sensors that produce this data are subject to degradation themselves, resulting in corruption of FOOMs. This paper reports a method of automating detection of sensor faults. It is the only known method that is capable of detecting such faults. The method is in essence a pair of novelty detection algorithms that produce measures of unusual counts of stress events at the level of the individual cell and unusual distributions of counts over the entire FOOM. Cell-level error is detected using a probability threshold and a sum of standard deviations. FOOM-level error is detected using a novel application of the Eigenface algorithm of Turk and Pentland [1]. These measures are used as inputs to a multi-layer perceptron (MLP) that is trained to classify FOOMs as normal or corrupted. Classification success is generally over 95%.

KW - sensor degradation

KW - eigenanalysis

KW - neural networks

KW - strain gauges

KW - RECOGNITION

M3 - Conference contribution

SN - 0-87849-839-7

SP - 391

EP - 400

BT - DAMAS 99: DAMAGE ASSESSMENT OF STRUCTURES

A2 - Gilchrist, MD

A2 - DulieuBarton, JM

A2 - Worden, K

PB - TRANSTEC PUBLICATIONS LTD

CY - ZURICH-UETIKON

T2 - 3rd International Conference on Damage Assessment of Structures (DAMAS 99)

Y2 - 28 June 1999 through 30 June 1999

ER -