Towards Robustness in Neural Network Based Fault Diagnosis

DOI10.2478/v10006-008-0039-2zbMath1155.93344OpenAlexW2126894374MaRDI QIDQ3601356

Krysztof Patan, Marcin Witczak, Józef Korbicz

Publication date: 10 February 2009

Published in: International Journal of Applied Mathematics and Computer Science (Search for Journal in Brave)

Full work available at URL: https://eudml.org/doc/207898

zbMATH Keywords

robustnessfault diagnosisdynamic neural networkGMDH neural network

Mathematics Subject Classification ID

Sensitivity (robustness) (93B35) Neural networks for/in biological studies, artificial life and related topics (92B20) Nonlinear systems in control theory (93C10) Application models in control theory (93C95)

Related Items

Local stability conditions for discrete-time cascade locally recurrent neural networks ⋮ Spike patterns and chaos in a map-based neuron model ⋮ Artificial intelligence methods in diagnostics of analog systems ⋮ An unscented Kalman filter in designing dynamic GMDH neural networks for robust fault detection

Cites Work

• Identification of parametric models from experimental data. Transl. from an upd. French version by the authors, with the help of John Norton
• Modelling and estimation strategies for fault diagnosis of non-linear systems. From analytical to soft computing approaches.
• Robust fault detection using analytical and soft computing methods
• Comparing different approaches to model error modeling in robust identification
• Set membership identification of nonlinear systems
• New soft computing techniques for system modelling, pattern classification and image processing.
• Approximation of state-space trajectories by locally recurrent globally feed-forward neural networks
• Fault Tolerant Control Design For Polytopic LPV Systems
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item