No abstract

The paper focuses on the application of neuro-fuzzy techniques in fault detection and isolation. The objective of this paper is to detect and isolate faults to an industrial gas turbine, with emphasis on faults occurred in the actuator part of the gas turbine. A neuro-fuzzy based learning and adaptation of TSK fuzzy models is used for residual generation, while for residual evaluation a neuro-fuzzy classifier for Mamdani models is used. The paper is concerned on how to obtain an interpretable fault classifier as well as interpretable models for residual generation. Copyright © 2002 IFAC

In this paper, a neuro-fuzzy and de-coupling fault diagnosis scheme (NFDFDS) is proposed for fault detection and isolation (FDI) of nonlinear dynamic systems. In this approach, powerful approximation and reasoning capabilities of neuro-fuzzy models are combined with the de-coupling capabilities of optimal observers to perform reliable fault detection and isolation. The neuro-fuzzy model presented here is a special form of Takagi-Sugeno (TS) fuzzy model used to represent the system by a fuzzy fusion of local linear sub-models. The necessary condition for the application of this FDI scheme is that this special form of the TS model can represent the nonlinear system, which is true for many practical systems. It is shown that if all the local models are stable and the corresponding local observers converge to the local models it can be expected that the global model is stable and the corresponding global observer will converge to the nonlinear input-output system. An application of FDI for an electro-pneumatic valve actuator in a sugar factory is presented. Key issues of finding a suitable structure for detecting and isolating nine realistic actuator faults are described.

No abstract

This paper presents a scheme for fault detection and isolation (FDI) of on-board gyroscope sensors and thrusters for spacecraft attitude control, based on the example of the Mars Express (MEX) satellite. The main contribution of the paper is related to the design and the optimization of an FDI procedure based on robust observers or filters, used as estimators, which generate the FDI residual signals. When organized into an estimator bank, excellent fault isolation properties are achieved upon suitable design. The residual evaluation relies on decision logic, whose thresholds are properly selected and specified. The FDI strategy is applied to the non-linear simulation of the MEX system, and the FDI performance is evaluated subject to disturbance signals, model uncertainty, and measurement noise processes. The robustness and reliability properties of the robust residual generators are investigated and verified in simulation by selecting suitable performance criteria together with Monte Carlo analysis. The results obtained highlight a good trade-off between solution complexity and achieved performances. Comparisons with the existing fault diagnosis algorithms implemented on board the MEX spacecraft are finally reported. The proposed FDI design methodology constitutes a reliability approach for real application of FDI in future spacecraft.