@inproceedings{ef98bbdfd8104c7ab0eb2d29906623cf,
title = "Intake Flow Rate Prediction Method Based on Radial Basis Function Network",
abstract = "The strong nonlinear feature of intake flow rate and the difficulty of accurately modelling control objects are challenging for an efficient flow rate regulation system of an aircraft engine high-altitude test stand. Manual regulation requires accumulated experience and is time and labour-consuming. To improve the regulation efficiency, this research proposes a data-driven method of predicting intake flow rate in the high-altitude test stand. We first designed a preliminary prediction scheme with radial basis function network and developed the detailed prediction method by analysing the input and output of the intake flow rate regulation system. The devised prediction method was then trained and tested by experimental data from the high-altitude test stand. Results show that the proposed method performs well in intake flow rate prediction and can efficiently assist the fast regulation of intake flow rate. By using a radial basis function network, the method demonstrates reliable performance and offers a promising solution for overcoming the challenges in manual regulation.",
keywords = "Intake flow rate, data-driven prediction, high-altitude test stand, radial basis function network",
author = "Guang Tan and Hui Tian and Gang Lv and Daoxin Wei and Zhuoqiang Chen",
note = "Publisher Copyright: {\textcopyright} 2025 The Authors.; 15th Asia Conference on Mechanical and Aerospace Engineering, ACMAE 2024 ; Conference date: 27-12-2024 Through 29-12-2024",
year = "2025",
doi = "10.3233/ATDE250083",
language = "英语",
series = "Advances in Transdisciplinary Engineering",
publisher = "IOS Press BV",
pages = "526--534",
editor = "Ben Guan",
booktitle = "Mechanical and Aerospace Engineering - Proceedings of the 15th Asia Conference on Mechanical and Aerospace Engineering, ACMAE 2024",
address = "荷兰",
}