|
|
| |
| 基于多可信度代理模型的导弹气动数据生成技术研究 |
| Research on missile aerodynamic data generation technology based on multi-credibility proxy model |
| 投稿时间：2024-06-12 修订日期：2024-07-24 |
| DOI： |
| 中文关键词: 气动数据 多可信代理模型 高低可信度样本点比例 K-means聚类算法 |
| 英文关键词:aerodynamic data multi-trusted proxy model the proportion of high and low confidence sample points K-means clustering algorithm |
| 基金项目:国家自然科学基金项目（面上项目，重点项目，重大项目） |
|
| 摘要点击次数: 113 |
| 全文下载次数: 0 |
| 中文摘要: |
| 代理模型是气动数据生成的新研究方向，传统的代理模型方法依赖于大量高精度仿真模型的样本点及其响应值来确保模型的精度，多可信度代理模型通过融合多层的高可信度和低可信度模型，能在保持一定精度的同时降低计算成本，对降低导弹研发周期有着重要意义。本文以Co-Kriging模型为代表，对不同数量的低可信度样本点对多可信度模型的影响与最佳的高低可信度样本点比例展开研究，并提出一种适用于气动数据的多可信度代理模型采样方法，该方法在利用高低可信度气动数据一一映射关系，在低可信度气动数据上使用K-means聚类算法获得训练用的高可信度气动数据对应位置。应用到导弹气动数据预测中到三种多可信度代理模型构建中，其中 Co-Kriging模型综合预测效果最优，推荐高低可信度样本数比例为1:4与1:3之间。 |
| 英文摘要: |
| Surrogate model is a new research direction of aerodynamic data generation, the traditional surrogate model method relies on a large number of high-precision simulation model sample points and their response values to ensure the accuracy of the model, and the multi-credibility surrogate model can reduce the computational cost while maintaining a certain accuracy by integrating multi-layer high and low credibility models, which is of great significance for reducing the missile development cycle. In this paper, the influence of different numbers of low-confidence sample points on the multi-confidence model and the optimal ratio of high-low-confidence sample points are studied, and a multi-confidence surrogate model sampling method suitable for pneumatic data is proposed. It is applied to the construction of three multi-credibility surrogate models in the prediction of missile aerodynamic data, among which the Co-Kriging model has the best comprehensive prediction effect. The recommended ratio of high and low confidence sample size is between 1:4 and 1:3. |
| 查看/发表评论 下载PDF阅读器 |
