12
views
0
recommends
+1 Recommend
1 collections
    0
    shares

      To publish with AIAA, please click here

      • Record: found
      • Abstract: found
      • Article: found

      Learning for Predictions: Real-Time Reliability Assessment of Aerospace Systems

      research-article

      Read this article at

      ScienceOpenPublisher
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Prognostics and health management aim to predict the remaining useful life (RUL) of a system and to allow a timely planning of replacement of components, limiting the need for corrective maintenance and the downtime of equipment. A major challenge in system prognostics is the availability of accurate physics-based representations of the faults dynamics. Additionally, the analysis of data acquired during flight operations is traditionally time consuming and expensive. This work proposes a computational method to overcome these limitations through the dynamic adaptation of the state-space model of fault propagation to onboard observations of the system’s health. Our approach aims at enabling real-time assessment of systems’ health and reliability through fast predictions of the remaining useful life that accounts for uncertainty. The strategy combines physics-based knowledge of the system damage propagation rate, machine learning. and real-time measurements of the health status to obtain an accurate estimate of the RUL of aerospace systems. The original method is demonstrated for the RUL prediction of an electromechanical actuator for aircraft flight controls. We observe that the strategy allows us to refine rapid predictions of the RUL in fractions of seconds by progressively learning from onboard acquisitions.

          Related collections

          Most cited references63

          • Record: found
          • Abstract: not found
          • Article: not found

          Stable signal recovery from incomplete and inaccurate measurements

            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Training feedforward networks with the Marquardt algorithm.

            The Marquardt algorithm for nonlinear least squares is presented and is incorporated into the backpropagation algorithm for training feedforward neural networks. The algorithm is tested on several function approximation problems, and is compared with a conjugate gradient algorithm and a variable learning rate algorithm. It is found that the Marquardt algorithm is much more efficient than either of the other techniques when the network contains no more than a few hundred weights.
              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              Karhunen–Loève procedure for gappy data

                Bookmark

                Author and article information

                Contributors
                Conference
                aiaaj
                AIAA Journal
                AIAA Journal
                American Institute of Aeronautics and Astronautics
                1533-385X
                14 September 2021
                February 2022
                : 60
                : 2
                : 566-577
                Affiliations
                Politecnico di Torino , 10129 Turin, Italy
                Author notes
                [*]

                Ph.D. Candidate, Department of Mechanical and Aerospace Engineering, c.so Duca degli Abruzzi 24. Student Member AIAA.

                [†]

                Assistant Professor, Department of Mechanical and Aerospace Engineering, c.so Duca degli Abruzzi 24.

                [‡]

                Adjunct Professor, Department of Mechanical and Aerospace Engineering, c.so Duca degli Abruzzi 24. Associate Fellow AIAA.

                Author information
                https://orcid.org/0000-0003-2672-2848
                https://orcid.org/0000-0002-3124-2198
                https://orcid.org/0000-0002-5969-9069
                Article
                J060664 J060664
                10.2514/1.J060664
                f8ee94e8-d873-42a5-90a1-d5796f45d0b6
                Copyright © 2021 by Pier Carlo Berri, Matteo D. L. Dalla Vedova, and Laura Mainini. Published by the American Institute of Aeronautics and Astronautics, Inc., with permission. All requests for copying and permission to reprint should be submitted to CCC at www.copyright.com; employ the eISSN 1533-385X to initiate your request. See also AIAA Rights and Permissions www.aiaa.org/randp.
                History
                : 24 February 2021
                : 10 July 2021
                : 09 August 2021
                Page count
                Figures: 9, Tables: 1
                Funding
                Funded by: Politecnico di Torinohttp://dx.doi.org/10.13039/100013000
                Award ID: Visiting Professor Grant under art.23 co.3 L240/10
                Categories
                Regular Articles

                Engineering,Physics,Mechanical engineering,Space Physics
                Engineering, Physics, Mechanical engineering, Space Physics

                Comments

                Comment on this article