arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2212.12207cs.CEcs.LGmath.OC
收藏

强化学习在型材挤出模具形状优化中的研究

Investigation of reinforcement learning for shape optimization of profile extrusion dies

Institute for Lightweight Design and Structural Biomechanics, TU Wien(维也纳工业大学轻量化设计与结构生物力学研究所);RWTH Aachen University(亚琛工业大学)

Clemens Fricke, Daniel Wolff, Marco Kemmerling, Stefanie Elgeti

AI总结:

本研究探讨了将强化学习应用于型材挤出模具形状优化的方法,通过自由变形技术修改流道几何,并在两个2D测试案例中验证了不同智能体及多环境并行训练对优化效率和进程的影响。

摘要:

型材挤出是一种利用熔融聚合物连续生产塑料型材的制造工艺。模具的设计尤为关键,熔体通过模具被挤压以获得所需形状。然而,由于模具出口处的速度分布不均匀或挤出物内部存在残余应力,制造部件的最终形状通常会偏离预期。为避免这些偏差,可以对模具形状进行计算优化,文献中已有使用经典优化方法对此进行研究的先例。\n形状优化领域的一种新方法是利用强化学习(RL)作为一种基于学习的优化算法。RL基于智能体与环境的试错交互。对于每个动作,智能体会获得奖励并被告知环境的后续状态。虽然对于单一问题,RL技术不一定优于经典优化算法(例如基于梯度或进化的算法),但当重复执行类似的优化任务时,RL技术有望表现得尤为出色,因为智能体学习到了一种更通用的生成最优形状的策略,而不是仅仅局限于单一问题。\n在本研究中,我们通过将该方法应用于两个2D测试案例来对其进行探索。RL智能体可以使用所谓的自由变形(Free-Form Deformation)来修改流道几何结构,该方法将计算网格嵌入到变换样条中,然后基于控制点位置对其进行操作。具体而言,我们研究了使用不同智能体对训练进度的影响,以及在训练过程中利用多个环境来节省实际运行时间的潜力。

英文摘要:

Profile extrusion is a continuous production process for manufacturing plastic profiles from molten polymer. Especially interesting is the design of the die, through which the melt is pressed to attain the desired shape. However, due to an inhomogeneous velocity distribution at the die exit or residual stresses inside the extrudate, the final shape of the manufactured part often deviates from the desired one. To avoid these deviations, the shape of the die can be computationally optimized, which has already been investigated in the literature using classical optimization approaches. A new approach in the field of shape optimization is the utilization of Reinforcement Learning (RL) as a learning-based optimization algorithm. RL is based on trial-and-error interactions of an agent with an environment. For each action, the agent is rewarded and informed about the subsequent state of the environment. While not necessarily superior to classical, e.g., gradient-based or evolutionary, optimization algorithms for one single problem, RL techniques are expected to perform especially well when similar optimization tasks are repeated since the agent learns a more general strategy for generating optimal shapes instead of concentrating on just one single problem. In this work, we investigate this approach by applying it to two 2D test cases. The flow-channel geometry can be modified by the RL agent using so-called Free-Form Deformation, a method where the computational mesh is embedded into a transformation spline, which is then manipulated based on the control-point positions. In particular, we investigate the impact of utilizing different agents on the training progress and the potential of wall time saving by utilizing multiple environments during training.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑