Proceedings ArticleDOI
A neural network based approach to fault diagnosis in aerospace systems
R. Saeks,M. Lothers,Robert M. Pap,K. Mach +3 more
- pp 271-273
Reads0
Chats0
TLDR
Results indicate that neural networks can generalize around the data on which they were trained, yielding better performance for unforeseen inputs than traditional algorithms in the case of the fault diagnosis problem described.Abstract:
A neural network based fault diagnosis system is being developed for use in aerospace systems in which a family of neural nets replaces an online simulation process A new neural network implementation of one of the model-based algorithms was developed The authors summarize a series of computer experiments designed to benchmark the performance of this neural network based fault diagnosis algorithm in an environment where the good components of the systems are only known up to a tolerance band The results indicate that neural networks can generalize around the data on which they were trained, yielding better performance for unforeseen inputs than traditional algorithms in the case of the fault diagnosis problem described >read more
Citations
More filters
Journal ArticleDOI
Computer Network Fault Diagnosis Based On Neural Network
TL;DR: The method is widely used, which is combined the self organizing feature map (SOM) neural network and multilayer feedforward neural network (BP) to improve the convergence the speed of BP neural network.
Dissertation
Dynamic Neural Network-based Pulsed Plasma Thruster (PPT) Fault Detection and Isolation for the Attitude Control Subsystem of Formation Flying Satellites
TL;DR: In this paper, the authors developed a dynamic neural network-based fault detection and isolation (FDI) scheme for the Pulsed Plasma Thrusters (PPTs) that are used in the Attitude Control Subsystem (ACS) of satellites that are tasked to perform a formation flying mission.
Proceedings ArticleDOI
An intelligent approach to sensor fusion-based diagnostics
R.G. Wright,L. Kirkland +1 more
TL;DR: This paper describes the integration of diverse sensor technology capable of analyzing units under test (UUT) from different perspectives, with advanced analysis techniques that provide new insight into static, dynamic, and historical UUT performance.
References
More filters
Journal ArticleDOI
Fuzzy min-max neural networks. I. Classification
TL;DR: The fuzzy min-max classifier neural network implementation is explained, the learning and recall algorithms are outlined, and several examples of operation demonstrate the strong qualities of this new neural network classifier.
Journal ArticleDOI
Node-fault diagnosis and a design of testability
TL;DR: A concept of k-node-fault testability is introduced and a sufficient and almost necessary condition for testability as well as the test procedure is presented, which depends only on the graph of the circuit, not on the element values.
Journal ArticleDOI
Analog Fault Diagnosis with Failure Bounds
TL;DR: A simulation-after-test algorithm for the analog fault diagnosis problem is proposed in which a bound on the maximum number of simultaneous failures is used to minimize the number of test points required.
Journal ArticleDOI
Representing and diagnosing dynamic process data using neural networks
TL;DR: The networks trained using raw time-series data were able to diagnose untrained single-fault patterns sampled earlier in the fault-induced transient, than the ones trained using moving average data, and the moving-average network performed as well as the time- series network.
Journal ArticleDOI
On the implementation of an analog ATPG: the nonlinear case
Chin-Long Wey,Richard Saeks +1 more
TL;DR: An analog Automatic Test Program Generation (ATPG) for linear circuits or systems is being developed that is subdivided into off-line and on-line components while the actual test can be run in either a fully automatic mode or interactively.