Scholarlink

<p>Dynamic multi-body simulation models of the entire system are particularly important for the development and analysis of gearboxes. With the help of these models, the operational behavior of the gearbox can be examined in detail, without having to produce a&#xa0;prototype. This makes it possible to investigate the influence of various factors, such as misalignments, deformations of components or the usage of different structural components, on the operational behavior of the gearbox. The modelling of the gear mesh is particularly relevant in order to be able to model the behavior of the gearbox realistically. If the gear mesh should be calculated with an enhanced level of detail, numerical FE-based tooth contact analyses are used for each integration step of the dynamic model. These calculate the forces and torques in all spatial directions on the gears based on translational and rotational positions of the gears in contact. However, the disadvantage of this highly precise method is the longer calculation time that results from solving the FE-based tooth contact for each calculation step and prevents efficient use in product development. To improve the calculation time of the model, an AI model, e.g. a&#xa0;neural network, will be used instead of the time-consuming FE-based tooth contact calculation. The neural network reduces the calculation time of the dynamic multi-body model from several hours to just a&#xa0;few minutes. This enables the efficient use of highly accurate gear modelling in dynamic multi-body simulation. The development is carried out as User Force in the simulation software Simpack.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Accelerating FE-based gear mesh calculations in dynamic multi-body simulations with AI

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年2月24日

查看全文
  • Marius Willecke,
  • Christian Westphal,
  • Christian Brecher

摘要

Dynamic multi-body simulation models of the entire system are particularly important for the development and analysis of gearboxes. With the help of these models, the operational behavior of the gearbox can be examined in detail, without having to produce a prototype. This makes it possible to investigate the influence of various factors, such as misalignments, deformations of components or the usage of different structural components, on the operational behavior of the gearbox. The modelling of the gear mesh is particularly relevant in order to be able to model the behavior of the gearbox realistically. If the gear mesh should be calculated with an enhanced level of detail, numerical FE-based tooth contact analyses are used for each integration step of the dynamic model. These calculate the forces and torques in all spatial directions on the gears based on translational and rotational positions of the gears in contact. However, the disadvantage of this highly precise method is the longer calculation time that results from solving the FE-based tooth contact for each calculation step and prevents efficient use in product development. To improve the calculation time of the model, an AI model, e.g. a neural network, will be used instead of the time-consuming FE-based tooth contact calculation. The neural network reduces the calculation time of the dynamic multi-body model from several hours to just a few minutes. This enables the efficient use of highly accurate gear modelling in dynamic multi-body simulation. The development is carried out as User Force in the simulation software Simpack.