Integrated in-Flight Fault Detection and Accommodation: A Model-Based Study

2007 ◽  
Vol 129 (4) ◽  
pp. 962-969 ◽  
Author(s):  
Randal T. Rausch ◽  
Kai F. Goebel ◽  
Neil H. Eklund ◽  
Brent J. Brunell

In-flight fault accommodation of safety-critical faults requires rapid detection and remediation. Indeed, for a class of safety-critical faults, detection within a millisecond range is imperative to allow accommodation in time to avert undesired engine behavior. We address these issues with an integrated detection and accommodation scheme. This scheme comprises model-based detection, a bank of binary classifiers, and an accommodation module. The latter biases control signals with pre-defined adjustments to regain operability while staying within established safety limits. The adjustments were developed using evolutionary algorithms to identify optimal biases off-line for multiple faults and points within the flight envelope. These biases are interpolated online for the current flight conditions. High-fidelity simulation results are presented showing accommodation applied to a high-pressure compressor fault on a commercial, high-bypass, twin-spool, turbofan engine throughout the flight envelope.

Author(s):  
Randal T. Rausch ◽  
Kai F. Goebel ◽  
Neil H. Eklund ◽  
Brent J. Brunell

In-flight fault accommodation of safety-critical faults requires rapid detection and remediation. Indeed, for a class of safety critical faults, detection within a millisecond range is imperative to allow accommodation in time to avert undesired engine behavior. We address these issues with an integrated detection and accommodation scheme. This scheme comprises model-based detection, a bank of binary classifiers, and an accommodation module. The latter biases control signals with pre-defined adjustments to regain operability while staying within established safety limits. The adjustments were developed using evolutionary algorithms to identify optimal biases off-line for multiple faults and points within the flight envelope. These biases are interpolated online for the current flight conditions. High-fidelity simulation results are presented showing accommodation applied to a high-pressure turbine fault on a commercial, high-bypass, twin-spool, turbofan engine throughout the flight envelope.


2016 ◽  
Vol 23 (19) ◽  
pp. 3175-3195 ◽  
Author(s):  
Ayan Sadhu ◽  
Guru Prakash ◽  
Sriram Narasimhan

A robust hybrid hidden Markov model-based fault detection method is proposed to perform multi-state fault classification of rotating components. The approach presented in this paper enhances the performance of the standard hidden Markov model (HMM) for fault detection by performing a series of pre-processing steps. First, the de-noised time-scale signatures are extracted using wavelet packet decomposition of the vibration data. Subsequently, the Teager Kaiser energy operator is employed to demodulate the time-scale components of the raw vibration signatures, following which the condition indicators are calculated. Out of several possible condition indicators, only relevant features are selected using a decision tree. This pre-processing improves the sensitivity of condition indicators under multiple faults. A Gaussian mixing model-based hidden Markov model (HMM) is then employed for fault detection. The proposed hybrid HMM is an improvement over traditional HMM in that it achieves better separation of the feature space leading to more robust state estimation under multiple fault states and measurement noise scenarios. A simulation employing modulated signals and two experimental validation studies are presented to demonstrate the performance of the proposed method.


Author(s):  
Jose Luis de la Vara ◽  
Arturo S. García ◽  
Jorge Valero ◽  
Clara Ayora

Author(s):  
Antoni Ligęza ◽  
Jan Kościelny

A New Approach to Multiple Fault Diagnosis: A Combination of Diagnostic Matrices, Graphs, Algebraic and Rule-Based Models. The Case of Two-Layer ModelsThe diagnosis of multiple faults is significantly more difficult than singular fault diagnosis. However, in realistic industrial systems the possibility of simultaneous occurrence of multiple faults must be taken into account. This paper investigates some of the limitations of the diagnostic model based on the simple binary diagnostic matrix in the case of multiple faults. Several possible interpretations of the diagnostic matrix with rule-based systems are provided and analyzed. A proposal of an extension of the basic, single-level model based on diagnostic matrices to a two-level one, founded on causal analysis and incorporating an OR and an AND matrix is put forward. An approach to the diagnosis of multiple faults based on inconsistency analysis is outlined, and a refinement procedure using a qualitative model of dependencies among system variables is sketched out.


Author(s):  
Stefan Gulan ◽  
Jens Harnisch ◽  
Sven Johr ◽  
Roberto Kretschmer ◽  
Stefan Rieger ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document