Optimization for Hot-film Anti-icing Structure by BPNN and GA

A coupled method combining the Back Propagation Neural Network (BPNN) and Genetic Algorithm (GA) was developed to optimize a 2D design of aero-engine inlet anti-icing structure, which has a cover on the film heating ejection slot. The optimal goal is to maximize the heating effectiveness which was u...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2021-02, Vol.1828 (1), p.12022
Main Authors: Liu, Jie, Ke, Peng
Format: Article
Language:English
Subjects:
Aeronautical engineering
Artificial neural networks
Back propagation networks
Deicing
Design optimization
Ejection
Engine inlets
Flow velocity
Genetic algorithms
Heating
Neural networks
Physics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A coupled method combining the Back Propagation Neural Network (BPNN) and Genetic Algorithm (GA) was developed to optimize a 2D design of aero-engine inlet anti-icing structure, which has a cover on the film heating ejection slot. The optimal goal is to maximize the heating effectiveness which was used to assess the performance of hot-air film. The film-heating ejection angle and the cover opening angle were selected as the design variables to be optimized. The training and testing samples employed in BPNN were obtained by numerical simulation, after which the objective function of GA was predicted. With a given flow rate of bled air, the optimal values of the two design variables were achieved as 22.6° and 15.1°, respectively. Compared to the previous optimal result of other researchers, the heating performance was improved by 16.7% with rapid progress. The result of this study illustrates that this hybrid optimal method can meet the accuracy requirements with high time-efficiency for optimization problems in aeronautics engineering.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1828/1/012022