Different approaches for gas path performance estimation of dynamic systems are commonly used, the most common being the variants of the Kalman filter. The extended Kalman filter (EKF) method is a popular approach for nonlinear systems which combines the traditional Kalman filtering and linearization techniques to effectively deal with weakly nonlinear and non-Gaussian problems. Its mathematical formulation is based on the assumption that the probability density function (PDF) of the state vector can be approximated to be Gaussian. Recent investigations have focused on the particle filter (PF) based on Monte Carlo sampling algorithms for tackling strong nonlinear and non-Gaussian models. Considering the aircraft engine is a complicated machine, operating under a harsh environment, and polluted by complex noises, the PF might be an available way to monitor gas path health for aircraft engines. Up to this point in time a number of Kalman filtering approaches have been used for aircraft turbofan engine gas path health estimation, but the particle filters have not been used for this purpose and a systematic comparison has not been published. This paper presents gas path health monitoring based on the PF and the constrained extend Kalman particle filter (cEKPF), and then compares the estimation accuracy and computational effort of these filters to the EKF for aircraft engine performance estimation under rapid faults and general deterioration. Finally, the effects of the constraint mechanism and particle number on the cEKPF are discussed. We show in this paper that the cEKPF outperforms the EKF, PF and EKPF, and conclude that the cEKPF is the best choice for turbofan engine health monitoring.
OPEN ACCESSEnergies 2013, 6 493
Abstract:The on-board sensor fault detection and isolation (FDI) system is essential to guarantee the reliability and safety of an aero engine. In this paper, a novel online sequential extreme learning machine with memory principle (MOS-ELM) is proposed for detecting, isolating, and reconstructing the fault sensor signal of aero engines. In many practical online applications, the sequentially coming data chunk usually possesses a characteristic of timeliness, and the overdue training data may mislead the subsequent learning process. The proposed MOS-ELM can improve the training process by introducing the concept of memory principle into the online sequential extreme learning machine (OS-ELM) to tackle the timeliness of the data chunk. Simulations on some time series problems and some benchmark databases show that MOS-ELM performs better in generalization performance, stability, and prediction accuracy than OS-ELM. The experiment results of the MOS-ELM-based sensor fault diagnosis system also verify the excellent generalization performance of MOS-ELM and indicate the effectiveness and feasibility of the developed diagnosis system.
Aircraft engine sensor fault diagnosis is closely related technology that assists operators in managing the health of gas turbine engine assets. As all gas turbine engines will exhibit performance changes due to usage, the on-board engine model built up initially will no longer track the engine over the course of the engine's life, and then the model-based method for sensor fault diagnosis tends to be failure. This necessitates the study of the sensor fault diagnosis techniques due to usage over its operating life. Based on our recent results, an integrated approach based on nonlinear on-board model is developed for the gas turbine engine sensor fault diagnostics in this paper. The architecture is mainly composed of dual nonlinear engine models; one is a nonlinear real-time adaptive performance model and the other a nonlinear onboard baseline model. The extended Kalman filter estimator in the nonlinear real-time adaptive performance model is used to obtain the real-time estimates of component performance, and the nonlinear on-board baseline model with performance periodically update to provide the nominal reference in flight. The novel update strategy to sensor fault threshold based on the model errors and noise level is also presented. Important results are obtained on step fault and pulse fault behavior of the engine sensor. The proposed approach is easy to design and tune with long-term engine health degradation. Finally, experiment studies are provided to validate the benefit of the engine sensor fault diagnostics.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.