Explore the vast range of titles available.

This study explores the impact of transfer learning on enhancing deep learning models for detecting defects in aero-engine components. We focused on metrics such as accuracy, precision, recall, and loss to compare the performance of models VGG19 and DeiT (data-efficient image transformer). RandomSearchCV was used for hyperparameter optimization, and we selectively froze some layers during training to help better tailor the models to our dataset. We conclude that the difference in performance across all metrics can be attributed to the adoption of the transformer-based architecture by the DeiT model as it does this well in capturing complex patterns in data. This research demonstrates that transformer models hold promise for improving the accuracy and efficiency of defect detection within the aerospace industry, which will, in turn, contribute to cleaner and more sustainable aviation activities.

In this work, a hot forming procedure is developed using computer-aided engineering (CAE) to produce thin Ti-6Al-4V sheet components in an effective way. Traditional forming methods involve time- and cost-consuming furnace heating and subsequent hot sizing steps. A material model for finite element (FE) analyses of sheet metal forming and springback at elevated temperatures in Ti-6Al-4V is calibrated and evaluated. The anisotropic yield criterion proposed by Barlat et al. 2003 is applied, and the time- and temperature-dependent stress relaxation behavior for elastic and inelastic straining are modeled using a Zener–Wert–Avrami formulation. Thermo-mechanical uniaxial tensile tests, a biaxial test, and uniaxial stress relaxation tests are performed and used as experimental reference to identify material model parameters at temperatures up to 700 °C. The hot forming tool setup is manufactured and used to produce double-curved aero engine components at 700 °C with different cycle times for validation purposes. Correlations between the predicted and measured responses such as springback and shape deviation show promising agreement, also when the forming and subsequent holding time was as low as 150 s. The short cycle time resulted in elimination of a detectable alpha case layer. Also, the tool surface coating extends the tool life in combination with a suitable lubricant.

The influence of Pt layer thickness on the fracture behavior of PtNiAl bond coats was studied in situ using clamped micro-beam bend tests inside a scanning electron microscope (SEM). Clamped beam bending is a fairly well established micro-scale fracture test geometry that has been previously used in determination of fracture toughness of Si and PtNiAl bond coats. The increasing amount of Pt in the bond coat matrix was accompanied by several other microstructural changes such as an increase in the volume fraction of α-Cr precipitate particles in the coating as well as a marginal decrease in the grain size of the matrix. In addition, Pt alters the defect chemistry of the B2-NiAl structure, directly affecting its elastic properties. A strong correlation was found between the fracture toughness and the initial Pt layer thickness associated with the bond coat. As the Pt layer thickness was increased from 0 to 5 µm, resulting in increasing Pt concentration from 0 to 14.2 at.% in the B2-NiAl matrix and changing α-Cr precipitate fraction, the initiation fracture toughness (K IC) was seen to rise from 6.4 to 8.5 MPa·m1/2. R-curve behavior was observed in these coatings, with K IC doubling for a crack propagation length of 2.5 µm. The reasons for the toughening are analyzed to be a combination of material's microstructure (crack kinking and bridging due to the precipitates) as well as size effects, as the crack approaches closer to the free surface in a micro-scale sample.

An aero engine failed due to the misalignment of the ball bearing fitted on the main shaft of the engine. The aero engine incorporates two independent compressors: a six-stage axial flow low-pressure compressor and a nine-stage axial flow high-pressure compressor. The bearing under consideration is a high-pressure-location bearing and is fitted at the rear of the nine-stage compressor. It was supposed to operate for at least 5000 h but failed catastrophically after 1300 h of operation and rendered the engine unserviceable. Unusually high stresses caused by misalignment and uneven axial loading resulted in the generation of fatigue crack(s) in the inner race. When the crack reached the critical size, the collar of the race fractured, causing subsequent damage. The cage also failed due to excessive stresses in the axial direction, and its material was smeared on the steel balls and the outer race.

The aero-engine casing, with its thin-walled complex structure, is a critical component that significantly influences machining quality due to its low-stiffness dynamic characteristics. In this study, we propose a multi-point flexible adaptive clamping technology to enhance the local stiffness of large-scale aero-engine casings. This approach aims to mitigate deformation during milling and drilling processes and improve precision throughout the multi-process machining procedure. Firstly, we analyze the milling and drilling processes involved in multi-process machining of aero-engine casings and construct a comprehensive error transfer model that considers both geometric errors and coupling effects caused by machining deformation. Furthermore, we elucidate the principles behind positioning using multi-point flexible clamping fixtures and controlling machining deformation. Finally, through simulation analysis of machining errors as well as actual machining experiments, we verify the effectiveness of our proposed multi-point flexible clamping fixture in suppressing deformation during milling and drilling processes. Our results demonstrate that this method effectively controls casing deformation during machining: it reduces flatness error at the casing mounting edge by 38.3%, while decreasing verticity error and position error at the casing mounting hole by 40.2% and 33.1%, respectively.

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.

Aero-engine blade is one of the core components of aero-engine and its safe service is crucial to the normal operation of aero-engine. Thus, it is very important to localize and quantify cracks of aero-engine blades to prevent safety accidents. To guarantee the structural health of aero-engine blades, the air-flow thermography (AFT) method which has advantages of non-contact, high performance, and sensitivity, was proposed for detection of the blade cracks. Firstly, the theoretical thermal response model was established and the crack simulation models with different depths were constructed. Then a detection system was established to detect the artificial cracks with different depths and orientations. Results showed that the proposed method can effectively quantify the cracks with different depths from 0.2 mm to 1.0 mm and characterize the crack orientations. In addition, the natural crack on the blade was detected and the principal component analysis (PCA) method was used to enhance the crack contrast with the background.

The aero-engine serves as the “heart” of an aircraft and is a primary factor determining the aircraft’s performance. Among the crucial components in the core of aero-engines, aero-engine compressor blades stand out as extremely important. They are not only numerous but also characterized by a multitude of parameters, making them the most complex parts in an aero-engine. This paper aims to address the trade-off between accuracy and efficiency in the existing measurement methods for asymmetric blades. Non-contact measurements were conducted using a structured light system composed of a stereo camera and a DLC projector. The point cloud data of the blades are processed using methods such as the PCA (Principal Component Analysis) algorithm, binary search, and least squares fitting. This paper established a fringe-projection profilometry light sensor system for the multi-view measurement of the blades. High-precision rotary tables are utilized to rotate and extract complete spatial point cloud data of aviation blades. Finally, measurements and comparative experiments on the blade body are conducted. The obtained blade point cloud data undergo sorting and denoising processes, resulting in improved measurement accuracy. The measurement error of the blade chord length is 0.001%, the measurement error of blade maximum thickness is 0.895%, compared to CMM (Coordinate Measuring Machine), where the measurement error of chord is 0.06%.

With the rapid development of the aviation industry, engines operate under extreme conditions of high temperature, high pressure, and high vibration, making them prone to surface damage such as ablation. Ablation not only affects the structural integrity of engine components but also threatens flight safety, making efficient and accurate detection of paramount importance. Traditional detection methods rely on manual visual inspection and non-destructive testing, which suffer from high subjectivity and low efficiency. In recent years, deep learning has achieved significant progress in industrial defect detection. However, conventional CNN-and Transformer-based architectures still suffer from substantial computational overhead and inadequate boundary segmentation accuracy in aero-engine ablation detection. This paper proposes a novel dual-pathway network Visual State-Space Residual Neural Network (VSS-ResNet) based on Mamba that combines Visual State Space (VSS) modules with ResNet50. This architecture leverages the global modeling capability of VSS modules and the local feature extraction capability of CNNs, effectively enhancing the accuracy and robustness of ablation boundary detection with the support of multi-scale feature fusion modules. Experimental results demonstrate that the proposed method achieves superior performance in mIoU, mPA, and Acc compared to mainstream segmentation models such as U-Net, Pyramid Scene Parsing Network (PSPNet), and DeepLab V3+ on a self-constructed engine endoscopic ablation dataset, validating its potential in intelligent aero-engine inspection.

To investigate the influence of ambient humidity on the aero-engine control plan, a twin-spool mixed-exhaust turbofan aero-engine is used as the research object. After establishing a numerical calculation model of the aero-engine using the component method and incorporating the humidity correction factor into the model, the mechanism of the influence of ambient humidity on the aero-engine’s control plan inflection point and performance is investigated. Furthermore, this paper examines the degradation factors of the performance parameters of each aero-engine component in the model, as well as the impact of the coupling effect of ambient humidity and the degradation of the performance parameters of each component on the aero-engine’s performance. The results show that the control plan inflection point shifts rightward when ambient humidity rises, increasing thrust output beyond the displacement point throughout ground tests, take-off, and cruising conditions. On the other hand, when deterioration and humidity work together, the original inflection point location is typically maintained, and very slight thrust variations occur. However, the growth rate of specific fuel consumption is far higher than when humidity effects are used alone. These results provide important information for enhancing the performance of aviation engines in different humidity and component degradation scenarios.