Early Fault Detection in Safety Critical Systems Using Complex Morlet Wavelet and Deep Learning

Author(s):  
A. Gandhimathinathan ◽  
R. Lavanya
Author(s):  
Yameen M. Hussain ◽  
Stephen Burrow ◽  
Leigh Henson ◽  
Patrick Keogh

This paper presents a review of techniques to mitigate jamming in Electromechanical Actuators (EMA) for safety critical applications in aerospace. Published progress to date is evaluated, with the remaining challenges highlighted. Through the use of Hierarchical Process Modelling (HPM), two key approaches to mitigate jamming were identified: (1) Fault Diagnostics (FD) and (2) Fault tolerant design. The development of a fault tolerant EMA system is currently at an early stage for implementation within safety critical systems due to the increased complexity of such systems (for example the anti-jamming system may require FD functionality itself). Challenges also exist for FD approaches particularly in achieving a robust means of fault detection. It is proposed that a hybrid FD approach, using a combination of model based and data-driven techniques to predict the onset of jamming, would be beneficial in capturing the discrepancies between the predicted and observed behaviour used to isolate and identify faults. Furthermore, several aspects of modelling and of data-driven methodologies for FD in the literature omit potentially important behaviours, and recommendations are made to improve upon this. For example, the simulation of faults in test stand analysis and the fidelity modelling of the motor and mechanical components are key areas to develop.


2020 ◽  
Vol 12 (3) ◽  
pp. 78-82 ◽  
Author(s):  
Alessandro Biondi ◽  
Federico Nesti ◽  
Giorgiomaria Cicero ◽  
Daniel Casini ◽  
Giorgio Buttazzo

2011 ◽  
Vol 31 (1) ◽  
pp. 281-285
Author(s):  
Huan HE ◽  
Zhong-wei XU ◽  
Gang YU ◽  
Shi-yu YANG

Sign in / Sign up

Export Citation Format

Share Document