Aerospace, Volume 10, Issue 1
2023 January - 90 articles
Cover Story: An adaptive deep transfer learning scheme is proposed for aircraft engine health prognosis under time-varying real flight conditions, which is usually a challenge in terms of data unavailability, complexity, and drift. Adaptive learning encapsulates long short-term memory to tackle data drift issues resulting in a massive change in data characteristics. Meanwhile, deep transfer learning adopts a pre-trained network over a sufficient number of degradation trajectories generated from health deterioration analysis software. The outcome is an excellent combination for overcoming data unavailability and complexity. This combination is used on the new commercial modular aero-propulsion system simulation dataset released by NASA, which exactly meets these criteria. The designed model, evaluated on several measures and visual interpretations, strongly supports the design results. View this paper - Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
- You may sign up for email alerts to receive table of contents of newly released issues.
- PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.