Topology optimization serves as a critical method for promoting lightweight structural design. Traditional methods predominantly focus on mechanical performance evaluation, often neglecting the critical correlation between modal characteristics and structural stiffness. The Evolutionary Structural Optimization (ESO) method is extensively employed in topology optimization; however, iterative oscillations lead to issues such as grid divergence and diminished solution quality. To address issues such as iterative oscillations and mesh divergence in the traditional Evolutionary Structural Optimization (ESO) method, this study applies a Simp Evolutionary Structural Optimization (SI-ESO) methodology. This method integrates intermediate density parameters and penalty factors into the progressive structural optimization process, thereby significantly enhancing iterative convergence and model quality. This work applied the optimized SI-ESO method to the lightweight redesign of an aviation generator’s rear cover, with validation conducted through additive manufacturing. Subsequently, the back cover of an aviation generator was redesigned and fabricated utilizing additive manufacturing technology. Empirical results indicate that under maximum stress conditions and employing the same additive process, the maximum deformation of the SI-ESO-optimized model is reduced compared to that of the ESO-designed model. Compared with the original design, the SI-ESO-optimized model achieved a 31% weight reduction, while relative to the ESO-optimized model, it exhibited a 27% lower maximum stress and a 10.53% higher first-order frequency, demonstrating both lightweighting and enhanced structural stiffness.

To address the issue of low accuracy and stability in traditional Convolutional Neural Networks (CNN)-based defect depth prediction for civil aircraft composites, we propose an improved Feature Enhancement Network (FEN)-CNN-Bidirectional Long Short-Term Memory (BiLSTM) impact damage depth prediction method. By integrating terahertz (THz) time-domain, frequency-domain, and absorbance spectroscopy with Confocal Laser Scanning Microscopy (CLSM) depth measurements, the correlation between THz spectral features and impact damage defect depth is systematically elucidated, thereby constructing a “THz features-depth” dataset. Furthermore, by leveraging the FEN model’s feature enhancement and denoising capabilities, along with the BiLSTM model’s bidirectional sequence modeling capability, the underlying relationship between terahertz spectral features and defect depth is deeply learned. This approach improves the stability and accuracy of spectral feature extraction by the CNN model under complex conditions. Ablation experiments revealed the improved model, compared to traditional CNN, reduced Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) by 43.08%, 44.4%, 57.18%, and 34.56%, respectively. Additionally, it decreased the Relative Standard Deviation (RSD) by 32.14%, and increased the Coefficient of Determination (R²) by 6.8%. Comparative experiments demonstrated the proposed model achieved an MSE of 0.0075 and an R² of 0.9539, outperforming other models. This study provides a novel method for precise low-velocity impact damage assessment in carbon fiber reinforced composites, enhancing safety evaluation for civil aircraft composite structures and contributing to aviation safety.