Aiming at the overfitting problem caused by the limited sample size in the spectral classification of aero-engine hot jets, this paper proposed a synthetic spectral enhancement classification network FTIR-SpectralGAN for the FT-IR of aeroengine hot jets. Firstly, passive telemetry FTIR spectrometers were used to measure the hot jet spectrum data of six types of aero-engines, and a spectral classification dataset was created. Then, a spectral classification network FTIR-SpectralGAN was designed, which consists of a generator and a discriminator. The generator architecture comprises six Conv1DTranspose layers, with five of these layers integrated with BN and LeakyReLU layers to introduce noise injection. This design enhances the generation capability for complex patterns and facilitates the transformation from noise to high-dimensional data. The discriminator employs a multi-task dual-output structure, consisting of three Conv1D layers combined with LeakyReLU and Dropout techniques. This configuration progressively reduces feature dimensions and mitigates overfitting. During training, the generator learns the underlying distribution of spectral data, while the discriminator distinguishes between real and synthetic data and performs spectral classification. The dataset was randomly partitioned into training, validation, and test sets in an 8:1:1 ratio. For training strategy, an unbalanced alternating training approach was adopted, where the generator is trained first, followed by the discriminator and then the generator again. Additionally, weighted mixed loss and label smoothing strategies were introduced to enhance network training performance. Experimental results demonstrate that the spectral classification accuracy reaches up to 99%, effectively addressing the overfitting issue commonly encountered in CNN-based classification tasks with limited samples. Comparative experiments show that FTIR-SpectralGAN outperforms classical data augmentation methods and CVAE-based synthetic data enhancement approaches. It also achieves higher robustness and classification accuracy compared to other spectral classification methods.

The infrared spectral features of aero-engine wake serve as a crucial basis for infrared detection, tracking, and identification of aircraft. Their spectral line structure is regulated by the concentration and temperature of the exhaust gases, as well as atmospheric absorption effects. This study employs a high-precision numerical simulation model and conducts field experiments on infrared spectral detection of exhaust plumes to systematically investigate the influence mechanisms of three factors—fuel–air ratio (achieved by varying exhaust gas concentration), exhaust temperature, and atmospheric absorption effects—on key spectral features, including peak intensity, line broadening, shape, and position. Results indicate the following. The fuel–air ratio enhances peak intensity and broadens spectral line width by increasing CO₂ and H₂O concentrations within the fuel-lean operating regime (f = 0.025–0.031); exhaust temperature causes exponential spectral intensity growth and line broadening by elevating molecular energy level populations, while inducing H₂O spectral band redshifts and fine-structure evolution; selective absorption by atmospheric H₂O, CO₂, and O₃ causes severe spectral attenuation near bands at 1041 cm⁻¹, 1590 cm⁻¹, 2349 cm⁻¹, and 3756 cm⁻¹, with transmittance distribution modulated by geographical and seasonal factors. This study provides theoretical support for wake spectral feature extraction, infrared stealth design, and detection/tracking identification.

This study proposes a numerical simulation-based computational model for engine nozzle parameters, establishing a dynamic mapping relationship between nozzle performance parameters and spectral-domain characteristics by coupling flow field properties with spectral radiation analysis. A 2D axisymmetric nozzle and plume flow field model was developed using the Reynolds-Averaged Navier-Stokes (RANS) turbulence model and the Discrete Ordinates (DO) radiation transfer method. The gas composition distribution and infrared radiation characteristics of an aeroengine under specific bypass ratios (BPR) and fuel flow rates were analyzed. Results indicate: (1) The maximum plume temperature reaches 1090 K, with peak H₂O and CO₂ concentrations of 2.61% and 2.72%, respectively; (2) Long-wave infrared (8.3–20 μm) exhibits the largest radiative area, while mid-wave infrared (3.8–8.3 μm) achieves the highest radiative intensity.