A VCA Combined MHSA-CNN for Aero-Engine Hot Jet Remote Sensing Mixed Spectral Feature Extraction
To address the challenges of spectral unmixing and feature extraction in the hot jet mixtures of two types of aero-engine hot jets, Fourier transform infrared spectrometry was employed to precisely measure these mixtures. The collected data encompassed the spectra of hot jets generated individually...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/7/1147 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | To address the challenges of spectral unmixing and feature extraction in the hot jet mixtures of two types of aero-engine hot jets, Fourier transform infrared spectrometry was employed to precisely measure these mixtures. The collected data encompassed the spectra of hot jets generated individually by the two distinct engine models, as well as those of the mutually mixed hot jets. In this paper, a mixed spectral unmixing algorithm based on VCA was put forward. Initially, the vertex component analysis (VCA) algorithm was utilized to decompose the mixed spectra. By comparing with the separately measured actual pure spectra, it was found that the mean RMSE of the hot jet pure spectra extracted by VCA for the two engines was 0.34846, and the mean SAM reached 0.00096, thus validating the effectiveness of the algorithm. Subsequently, the least squares (LS) algorithm was applied to ascertain the abundance values of the mixed spectra. Among the mixed samples, the average abundance values of the two pure spectra were 0.78 and 0.22, respectively. To further extract the spectral features after unmixing, an innovative one-dimensional convolutional multi-head self-attention mechanism neural network (MHSA-CNN) algorithm was devised in this study. This algorithm can accurately pinpoint the key wave crests of the features at 2282–2283 cm<sup>−1</sup> and 2388–2389 cm<sup>−1</sup>. The research findings offer crucial technical backing for the intelligent fault diagnosis of aero-engines and contribute to enhancing the accuracy and reliability of engine operating condition monitoring. |
|---|---|
| ISSN: | 2072-4292 |