Computation-Efficient Fault Detection Framework for Partially Known Nonlinear Distributed Parameter Systems

doi:10.1109/TNNLS.2023.3263840

Computation-Efficient Fault Detection Framework for Partially Known Nonlinear Distributed Parameter Systems

2024-09-01

1

PRE

AI

DOI：10.1109/TNNLS.2023.3263840

Original

Original request for help

Save

Abstract

En 中文

Fault detection for distributed parameter systems (DPSs) generally requires the complete model information to be known so far. However, for numerous industrial applications, it is common that accurate first-principles physical models are extremely difficult to obtain. Hence, the applicability of traditional model-based methods is being restricted. To pave the way, an adaptive neural network (AdNN) is constructed to simultaneously estimate the state variable and the unknown nonlinearity for a class of partially known nonlinear DPSs. Moreover, considering that full-state measurement is unrealistic in applications, the proposed adaptive neural observer is based on a reduced-order model, which also increases the computation efficiency. Then, the residual generation and evaluation are conducted using the output estimation error of the proposed adaptive neural observer. Bearing the effects of the neglected fast dynamics in mind, a data-driven threshold generation scheme is proposed. Extensive experimental results are presented and analyzed to validate the effectiveness of the proposed method.

Keywords:

Fault detection

Observers

Eigenvalues and eigenfunctions

Mathematical models

Fault diagnosis

Reduced order systems

Adaptive systems

Distributed parameter systems (DPSs)

fault detection

neural networks (NNs)

Computation-Efficient Fault Detection Framework for Partially Known Nonlinear Distributed Parameter Systems

Abstract

Journal

Organization