Civil aircraft health management research based on big data and deep learning technologies

the coupling and correlation degree between aircraft systems is higher, and the diagnosis and prognosis of aircraft are more complex. Building a platform for storing and analyzing the aviation big data becomes an important task for civil aviation. This paper proposes a civil aircraft health management big data architecture. The civil aircraft health management system includes airborne PHM, ground PHM, remote diagnosis system, portable maintenance assistant system, maintenance center, automatic test equipment, special test equipment. Airborne PHM collects data from multiple types of data sources. Ground PHM provides decision making support for civil aircrafts including real-time alarm, health management, maintenance plan, spare parts. The paper introduces deep learning algorithm and aircraft fault diagnosis and prognosis implementation.

[1]  Xin Zhou,et al.  Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data , 2016 .

[2]  Haidong Shao,et al.  Rolling bearing fault diagnosis using an optimization deep belief network , 2015 .

[3]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[4]  Andrew D. Ball,et al.  An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks , 2014, Expert Syst. Appl..

[5]  William Scheuren,et al.  Joint Strike Fighter Prognostics and Health Management , 1998 .

[6]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[7]  Yi Yang,et al.  A integrated vehicle health management framework for aircraft — A preliminary report , 2015, 2015 IEEE Conference on Prognostics and Health Management (PHM).

[8]  Diego Cabrera,et al.  Multimodal deep support vector classification with homologous features and its application to gearbox fault diagnosis , 2015, Neurocomputing.

[9]  Xue Sen Lin,et al.  Engine components fault diagnosis using an improved method of deep belief networks , 2016, 2016 7th International Conference on Mechanical and Aerospace Engineering (ICMAE).

[10]  Pingfeng Wang,et al.  Failure diagnosis using deep belief learning based health state classification , 2013, Reliab. Eng. Syst. Saf..

[11]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[12]  Guigang Zhang,et al.  Aviation PHM system research framework based on PHM big data center , 2016, 2016 IEEE International Conference on Prognostics and Health Management (ICPHM).

[13]  Pingfeng Wang,et al.  Deep Belief Network based state classification for structural health diagnosis , 2012, 2012 IEEE Aerospace Conference.