Safety Boundary Extraction Using FCM and Prediction Using ELM for Aero-engine Performance Parameters*

Author(s):  
Yingshun Li ◽  
Danyang Li ◽  
Ximing Sun ◽  
Xiaojian Yi
2012 ◽  
Vol 2012 ◽  
pp. 1-14
Author(s):  
Chunxiao Zhang ◽  
Junjie Yue

The prediction of the aero-engine performance parameters is very important for aero-engine condition monitoring and fault diagnosis. In this paper, the chaotic phase space of engine exhaust temperature (EGT) time series which come from actual air-borne ACARS data is reconstructed through selecting some suitable nearby points. The partial least square (PLS) based on the cubic spline function or the kernel function transformation is adopted to obtain chaotic predictive function of EGT series. The experiment results indicate that the proposed PLS chaotic prediction algorithm based on biweight kernel function transformation has significant advantage in overcoming multicollinearity of the independent variables and solve the stability of regression model. Our predictive NMSE is 16.5 percent less than that of the traditional linear least squares (OLS) method and 10.38 percent less than that of the linear PLS approach. At the same time, the forecast error is less than that of nonlinear PLS algorithm through bootstrap test screening.


2012 ◽  
Vol 490-495 ◽  
pp. 176-181 ◽  
Author(s):  
You Gao ◽  
Nan Wang

The maintenance and management of civil aero-engine require advanced monitor schemes to evaluate aero-engine health and condition in order to ensure safety of aircraft and increase life of aero-engine. In this paper, we adopted Kalman filter approach to monitor an aero-engine health and condition by building prediction models of main aero-engine performance parameters (EGT, N1, N2 and WF). The AR model is introduced into the Kalman filter equations, which is a helpful technique to improve the accuracy of monitoring models of performance parameters. When the relative error goes beyond ±0.3%, alarms will be given. The prediction results show that Kalman filter theory using for AR regression prognostic is an effective approach in aero-engine monitoring.


2013 ◽  
Author(s):  
Xiao-bo Zhang ◽  
Zhan-xue Wang ◽  
Zeng-wen Liu

Author(s):  
Sajath Kumar Manoharan ◽  
Kasram Santhosh ◽  
Mahesh P. Padwale ◽  
G. P. Ravishankar

Evaluation of engine performance during armament firing in fighter aircraft is a vital qualification aspect for airframe engine integration. Ingestion of missile’s efflux into air intake results in rapid increase of engine inlet temperatures (temperature ramps) which cause flow disturbance to the compressor. Temperature distortion caused due to armament firing and its effect on compressor stability during flight testing is evaluated. Accordingly mitigation actions are recommended for stall/surge free operations. Distortion descriptors are assessed using simulation model (engine performance program) and results compared with engine distortion limits.


2019 ◽  
Author(s):  
Maria Grazia De Giorgi ◽  
Giuseppe Ciccarella ◽  
Antonio Ficarella ◽  
Donato Fontanarosa ◽  
Elisa Pescini

Author(s):  
Caetano Peng

This paper highlights some engine non-linearities that can affect both performance and robustness of aero engines. It pays particular attention to non-linearities generated at the stator vane contact end joints. These non-linearities resulting from friction contact joints affect the vane modeshapes, damping and forced response. This work proposes upper and lower bound solutions based on vane end restraints non-linearities to predict conservative forced response of stator vanes. Some non-linearities such as those caused by mistuning can be beneficial to the component and system. There are also non-linearities that can be detrimental to engine performance, robustness and reliability. Moreover, it proposes and discusses the concept of temporal HCF or CCF lifing method. Recent developments in FE, CFD, mistuning, forced response and probabilistic codes can help to create more integrated design tools that incorporate time-dependent non-linearities in the lifing of aero engine components. Computations performed here demonstrated some level of component virtual testing. These analyses are important component virtual testing that will be gradually extended to whole aero engine virtual testing.


Sign in / Sign up

Export Citation Format

Share Document