Construction of End-to-End Machine Learning Surrogate Model and Its Application in Detonation Driving Problem
-
摘要: 人工智能可以发现数据中隐藏的物理规律，机器学习可以用来定制并建立实验参数与实验结果数据之间的关联关系，端到端代理模型则可以实现工程问题的快速设计、高精度预测和敏捷迭代，特别适合于解决强非线性爆炸与冲击动力学的工程问题。该论文选择了一个经典的爆轰驱动问题作为研究对象，并采用数值模拟数据作为机器学习的输入和输出。将正向模拟和逆向设计有机结合起来，构建端到端代理模型并验证模型的实用性和计算精确度。研究结果可以增强使用人工智能机器学习方法解决工程问题的信心，同时也为快速设计、高精度预测和敏捷迭代的实际应用奠定基础。
-
关键词:
Abstract: Artificial intelligence can discover hidden physical laws in data. Machine learning can be used to customize and establish the relationship between experimental parameters and experimental result data. End-to-end surrogate model can realize rapid design, high-precision prediction and agile iteration of engineering problems. They are especially suitable for solving the engineering problems of strongly nonlinear explosion and impact dynamics. The paper chosed a classic detonation driving problem as the research object and used numerical simulation data as the input and output of machine learning. Integrating forward simulation and reverse design organically, constructing an end--
Key words:
- Computational mechanics of explosion /
- Detonation drive /
- Artificial intelligence /
- Machine /
-
计量
- 文章访问数: 76
- HTML全文浏览量: 4
- PDF下载量: 46
- 被引次数: 0
下载: