相关实验视频
Updated: Sep 8, 2025

Surrogate Model Development for Digital Experiments in Welding
Published on: March 28, 2025
通过用机器学习替代模型替换分子动力学计算来加快多级力场参数优化
Robin Strickstrock1, Alexander Hagg1, Dirk Reith1,2
1Department of Engineering and Communication (DEC), Institute of Technology, Resource and Energy-efficient Engineering (TREE), Bonn-Rhein-Sieg University of Applied Sciences, 53757, Sankt Augustin, Germany.
机器学习模型通过取代缓慢的分子动力学模拟来显著加速力场参数的优化. 这种数据驱动的方法将计算时间缩短约20倍,同时保持高质量的力场用于分子建模.
科学领域:
- 计算化学和材料科学
- 机器学习在科学建模中的应用
背景情况:
- 分子建模依赖于精确的力场 (FFs) 来预测系统属性.
- 优化力场参数 (FFParam) 对于提高FF准确性和适用性至关重要.
- 传统的FF优化涉及耗时的分子动力学 (MD) 模拟.
研究的目的:
- 为了加速多尺度力场参数优化过程.
- 用机器学习 (ML) 替代模型替换计算上昂贵的MD模拟.
- 在分子建模中优化碳和的伦纳德-斯参数.
主要方法:
- 开发和实施机器学习替代模型.
- 在多尺度FParam优化工作流程中用ML替代品替换MD模拟.
- 优化侧重于Lennard-Jones对n-octane的参数,目标是形态能量和散装密度.
主要成果:
- 通过用ML替代品取代MD模拟,实现了大约20的加速度因子.
- 保持优化力场的质量与传统方法相比.
- 介绍了一个全面的工作流程,用于获取和准备ML替代模型培训.
结论:
- 机器学习替代模型为力场参数优化提供了显著的加速.
- 这种数据驱动的方法保持了力场的精度,同时大大降低了计算成本.
- 提出的方法使分子建模工具的开发和应用更有效.
相关概念视频
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Maxwell-Boltzmann Distribution: Problem Solving
This distribution function f(v) is defined by saying that the expected number N (v1,v2) of particles with speeds between v1 and v2 is given by
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
Modeling and Similitude
Three-Dimensional Force System:Problem Solving
To solve a three-dimensional force system, first resolve each force into its respective scalar components. Do this using...
Typical Model Studies

