On the Utilization of Fuzzy Rule-Based Systems for Productivity Estimations in Aircraft Final Assembly Lines

Tengfei Long, Zhentao Wang, Lara Harris, Arivazhagan Anbalagan, Jie Zhang

Research output: Chapter in Book/Report/Conference proceedingConference proceedingpeer-review

Abstract

In this paper, fuzzy rule-based systems (FRBSs) are introduced for productivity estimations in aircraft final assembly lines. While linear regressions have the direct explanatory ability, they lack the capability to capture nonlinearity. With a more complex structure, other ensemble-based methods such as random forests and gradient-enhanced regression trees can provide better accuracy but sacrifice model interpretability. By adopting a multi-objective optimization, the structure of FRBSs can be simplified, leading to enhanced transparency. In addition, considering the highly customized nature of aircraft, this paper explores a potential solution for predicting productivity in cases where it is not feasible to construct independent data-driven models, specifically for modified types. Preliminary findings suggest that FRBSs show promising potential as a viable alternative compared to other available options. The adoption of multi-objective optimization, the exploration of predicting productivity for modified types, and the interpretation of fuzzy rules contribute to the advancements in both accuracy and interpretability in the field.

Original languageEnglish
Title of host publication2023 IEEE 19th International Conference on Automation Science and Engineering, CASE 2023
PublisherIEEE
ISBN (Electronic)9798350320695
ISBN (Print)9798350320701
DOIs
Publication statusE-pub ahead of print - 28 Sept 2023
Event19th International Conference on Automation Science and Engineering - Auckland, New Zealand
Duration: 26 Aug 202330 Aug 2023

Publication series

NameIEEE International Conference on Automation Science and Engineering (CASE)
PublisherIEEE
ISSN (Print)2161-8070
ISSN (Electronic)2161-8089

Conference

Conference19th International Conference on Automation Science and Engineering
Country/TerritoryNew Zealand
CityAuckland
Period26/08/2330/08/23

Keywords

  • productivity estimations
  • aircraft final assembly line
  • fuzzy rule-based systems
  • interoperability

Fingerprint

Dive into the research topics of 'On the Utilization of Fuzzy Rule-Based Systems for Productivity Estimations in Aircraft Final Assembly Lines'. Together they form a unique fingerprint.

Cite this