Objective Functions of Predictive Models in Maintenance, Repairs, and Overhaul Organizations

Predictive maintenance is data-driven fault diagnosis and prognosis technique designed to reduce unscheduled maintenance and increase aircraft in-service operations time. The traditional approach of assessing predictive maintenance models in the aviation industry is based on a technical score like accuracy, precision, recall and F-metrics. Nevertheless, the model with the highest technical score does not necessarily lead to the highest financial savings and even can result in the additional costs for the business. At the same time, the highest financial saving in aircraft predictive maintenance could be achieved through the predictive model with a relatively small technical score. In this paper the authors analyse the efficiency of using the financial savings target function compared to technical scores, describes the boundaries of each approach’s application, and provides a systematic description of the methodology for calculating the financial savings function for maintenance, repair, and overhaul organizations. The approach proposed in the article supports maintenance, repair, and overhaul organizations increase efficiency in predictive maintenance activity, will increase repayment of predictive maintenance, and will provide a clear picture of how to allocate and prioritize resources in such projects.

• Record URL:
  • https://doi.org/10.1007/978-3-030-68476-1
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/9783030684754
• Supplemental Notes:
  • © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.
• Corporate Authors:

  Springer International Publishing

  ,    
• Authors:
  • Fedorov, Roman
  • Pavlyuk, Dmitry
  • Rozhkova, Lubov
  • Tyncherov, Timur
• Conference:
  • 20th International Conference on Reliability and Statistics in Transportation and Communication (RelStat2020)
  • Location: Riga , Latvia
  • Date: 2020-10-14 to 2020-10-17
• Publication Date: 2021-2

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 151-163
• Monograph Title: Reliability and Statistics in Transportation and Communication: Selected Papers from the 20th International Conference on Reliability and Statistics in Transportation and Communication, RelStat2020, 14-17 October 2020, Riga, Latvia
• Serial:
  • Lecture Notes in Networks and Systems
  • Volume: 195
  • Publisher: Springer Cham
  • ISSN: 2367-3370
  • Serial URL: https://www.springer.com/series/15179

Subject/Index Terms

• TRT Terms: Aircraft; Maintenance; Predictive models; Savings
• Subject Areas: Aviation; Finance; Maintenance and Preservation; Planning and Forecasting;

Filing Info

• Accession Number: 01881006
• Record Type: Publication
• ISBN: 9783030684754
• Files: TRIS
• Created Date: Apr 25 2023 9:42AM