关键词: 性能预测, 三维非对称喷管, NSGA-III-SAM算法, 壁面最优压力特征, 1D-CNN 模型

Abstract: The exhaust characteristics of a nozzle directly affect the overall performance of the scramjet engine. It is crucial to effective-ly predict the nozzle performance to prevent drastic changes for the stable operation of the engine. Numerical simulations of three-dimensional asymmetric nozzles under different flight conditions were conducted to build a dataset for predicting noz-zle performance under various Mach numbers and nozzle pressure ratios. Considering the limitations of traditional multi-objective optimization algorithms, a Non-dominated Sorting Genetic Algorithm-III-Simulated Annealing Mutation (NSGA-III-SAM) was proposed to extract optimal wall pressure measurement points for the nozzle. By using the optimal pressure characteristic data as input and the axial thrust coefficient, pitching moment coefficient, and lift coefficient as outputs, a nozzle performance parameter prediction model based on One Dimension-Convolutional Neural Network (1D-CNN) was established and validated by the data of over-expanded states at Mach numbers from 4.5 to 6.0. The results show that the optimal pressure positions extracted by the NSGA-III-SAM algorithm enable the model to have high-precision and rapid pre-diction performance, with the average absolute error of all performance parameters within 0.5%, and the maximum absolute error not exceeding 0.8%, and the average prediction time is only about 0.6ms. The constructed prediction model and method provide a reliable technical foundation for monitoring nozzle performance and adjusting exhaust conditions.

Key words: Prediction of performance parameters, Three-dimensional asymmetric nozzles, NSGA-III-SAM algorithm, Wall-optimized pressure measurement points, 1D-CNN model