On‐line learning neural networks for sensor validation for the flight control system of a B777 research scale model

Abstract

SUMMARYThis paper focuses on the analysis of a scheme for sensor failure, detection, identification and accommodation (SFDIA) using experimental flight data of a research aircraft model. Recent technical literature has shown the advantages of time-varying estimators and/or approximators. Conventional approaches are based on different versions of observers and Kalman filters while more recent methods are based on different approximators based on neural networks (NNs). The approach proposed in the paper is based on the use of on-line learning nonlinear neural approximators.The characteristics of three different neural architectures were compared through different sensor failures. The first architecture is based on a multi layer perceptron (MLP) NN trained with the extended back propagation algorithm (EBPA). The second and third architectures are based on a radial basis function (RBF) NN trained with the minimal resource allocating network (MRAN) and extended-MRAN (EMRAN). The MRAN and EMRAN algorithms have recently been developed for RBF networks and have shown remarkable learning capabilities at a fraction of the memory requirements and computational effort typically associated with conventional RBF NNs.The experimental data for this study are flight data acquired from the flight-testing of a 1 24 th semi-scale B777 research model designed, built, and flown at West Virginia University (WVU).

AI-Based Actuator/Sensor Fault Detection With Low Computational Cost for Industrial Applications

“…4e respectively. In the former figure the AD/IF on the current measurement, f aii are described by (5). The latter is a ramp type signal with σ i slope superimposed with a low frequency random signal with band-limited white noise characteristics as it was previously explained.…”

“…This is because the stability and performance of the plant under control depends on them and because failures on those components occur on a relatively regular basis [5]- [7]. Consequently, the FDI unit must be able to detect and isolate any faulty sensors (and/or actuators) based on their readings, and then the controller must be reconfigured to maintain the performance using the remaining healthy sensors (and/or actuators).…”

Cooperative Virtual Sensor for Fault Detection and Identification in Multi-UAV Applications

“…Statistical change detection filters as the CUSUM filter [33] can be used for robust detection of faults. This filter is used to detect both positive and negative changes in the mean value of the residual r k caused by the occurrence of a fault.…”

Neural Network based Sensor Fault Detection for Flight Control Systems

“…By using MATLAB and the data given by above equations, Nz(s) is given by Nz(s) = H(s)δc(s) + G(s)q(s) (11) where,…”

“…G Campa et al developed on-line learning neural networks for sensor validation for the flight control system of a B777 research scale model [11]. They used nonlinear neural approximates for sensor validation.…”