Research on Turbocharger Surge Detection Based on Multi-Domain Composite Features of Acoustic Signals

2025-01-8253

04/01/2025

Features
Event
WCX SAE World Congress Experience
Authors Abstract
Content
Taking a certain type of diesel engine turbocharger as the research object, a detailed study on the identification of turbocharger surge based on non-intrusive acoustic signals was conducted, and a novel turbocharger surge identification method based on multi-domain composite features of acoustic signals was proposed. The data related to the acoustic signals were collected through a series of supercharger surge reproduction experiments, and subsequently, a comprehensive database of these acoustic signals was established. Based on the multi-domain perspective of the time domain and frequency domain, 35 specific features were selected and extracted; the contribution of each individual feature to the occurrence of wheezing was calculated using the random forest algorithm, and the core contributing features were selected to be combined into a comprehensive multi-domain composite feature. This composite feature was then used for the recognition of turbocharger surge, serving as a highly sensitive indicator of wheezing acoustic signals. A support vector machine was utilised to build a robust model for the identification of wheezing, and the coefficients of the kernel function of the support vector machine were carefully optimised using the whale optimisation algorithm. Multiple sets of acoustic signals were obtained from the supercharger bench test, and the multi-domain composite feature was calculated to verify the accuracy of the model, which demonstrated an accuracy exceeding 99%.
Meta TagsDetails
DOI
https://doi.org/10.4271/2025-01-8253
Pages
9
Citation
Zhu, J., Zheng, H., and Zong, C., "Research on Turbocharger Surge Detection Based on Multi-Domain Composite Features of Acoustic Signals," SAE Technical Paper 2025-01-8253, 2025, https://doi.org/10.4271/2025-01-8253.
Additional Details
Publisher
Published
Apr 01
Product Code
2025-01-8253
Content Type
Technical Paper
Language
English