TY - GEN
T1 - Neural fault detection, isolation, and estimation design
AU - Chiang, Chi Yuan
AU - Juang, Jyh Ching
AU - Youssef, Hussein M.
PY - 1993
Y1 - 1993
N2 - For autonomous and high performance systems, onboard fault detection, isolation, and estimation (FDIE) against sensor, actuator, and system failures are important features in ensuring performance and avoiding catastrophes. Existing FDIE designs can be roughly classified as trail-and-error. hardware redundancy, model-based analytic redundancy, or knowledge based expert system approaches. All are subject to, fully or partly, uncertainty, nonlinearity, and complexity, leading to high false alarm rate or erroneous classification. In this paper, a neural FDIE scheme is developed and verified using simulated data. The neural FDIE scheme has the following advantages: robustness against unmodeled dynamics; ability in handling nonlinear dynamics; flexibility in accounting for both discrete (jump) behavior and continuous degradation; modular and systematic design; and potential for unanticipated failures. The FDIE scheme is based on the general regression neural network (GRNN) concept, making the FDIE easy and fast to train. The design is verified using an F/A-18 system. A class of failure patterns are simulated. The performance and property of the neural FDIE scheme are assessed.
AB - For autonomous and high performance systems, onboard fault detection, isolation, and estimation (FDIE) against sensor, actuator, and system failures are important features in ensuring performance and avoiding catastrophes. Existing FDIE designs can be roughly classified as trail-and-error. hardware redundancy, model-based analytic redundancy, or knowledge based expert system approaches. All are subject to, fully or partly, uncertainty, nonlinearity, and complexity, leading to high false alarm rate or erroneous classification. In this paper, a neural FDIE scheme is developed and verified using simulated data. The neural FDIE scheme has the following advantages: robustness against unmodeled dynamics; ability in handling nonlinear dynamics; flexibility in accounting for both discrete (jump) behavior and continuous degradation; modular and systematic design; and potential for unanticipated failures. The FDIE scheme is based on the general regression neural network (GRNN) concept, making the FDIE easy and fast to train. The design is verified using an F/A-18 system. A class of failure patterns are simulated. The performance and property of the neural FDIE scheme are assessed.
UR - http://www.scopus.com/inward/record.url?scp=0027848496&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0027848496&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0027848496
SN - 0780314212
T3 - Proceedings of the International Joint Conference on Neural Networks
SP - 1773
EP - 1776
BT - Proceedings of the International Joint Conference on Neural Networks
A2 - Anon, null
PB - Publ by IEEE
T2 - Proceedings of 1993 International Joint Conference on Neural Networks. Part 2 (of 3)
Y2 - 25 October 1993 through 29 October 1993
ER -