Design for Manufacturing: A Manufacturability Knowledge-Integrated Reinforcement Learning Framework for Free-Form Pipe Routing in Aeroengines

📄 arXiv: 2605.20644v1 📥 PDF

作者: Caicheng Wang, Zili Wang, Shuyou Zhang, Yongzhe Xiang, Zheyi Li, Liangyou Li, Jianrong Tan

分类: cs.LG, cs.AI, cs.RO

发布日期: 2026-05-20


💡 一句话要点

提出FPRO框架以解决航空发动机管道布置的可制造性问题

🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture)

关键词: 航空发动机 管道布置 强化学习 制造知识 路径优化 几何设计 智能制造

📋 核心要点

  1. 现有管道布置方法与下游制造脱节,导致设计过程繁琐且效率低下。
  2. 提出FPRO框架,通过强化学习与制造知识结合,优化航空发动机管道的布置。
  3. 实验结果显示,FPRO在路径生成的可制造性和几何平滑性上显著优于传统方法。

📝 摘要(中文)

制造设计在先进航空发动机开发中至关重要,复杂组件的制造性需要仔细考虑。然而,当前的管道布置实践与下游制造大多脱节,导致需要大量的试错迭代以实现可制造的设计。为了解决这一问题,本研究提出了基于Frenet的管道布置优化(FPRO)框架,这是一种集成制造知识的强化学习方法,旨在航空发动机的自由形状管道设计中。FPRO将布置问题表述为Frenet框架中的边值问题,管道路径通过曲率和扭转轮廓表示,并使用三次Hermite插值生成。为了整合设计与制造,特定领域的制造知识作为曲率和扭转的可接受范围约束嵌入。路径优化采用近端策略优化算法,结合随机探索和阶段引导奖励机制。实验结果表明,FPRO生成的路径在几何轮廓上更平滑且无碰撞,且在终端对齐、路径长度、障碍物规避和可制造性方面优于现有强化学习基线。

🔬 方法详解

问题定义:本研究旨在解决航空发动机管道布置中的可制造性问题。现有方法往往与制造过程脱节,导致设计迭代繁琐且效率低下。

核心思路:FPRO框架通过将管道布置问题转化为Frenet框架中的边值问题,结合制造知识约束,优化管道路径设计,以提高可制造性。

技术框架:FPRO框架包括路径表示、制造知识嵌入、路径优化和运动轨迹映射四个主要模块。路径通过曲率和扭转轮廓表示,优化过程采用近端策略优化算法。

关键创新:FPRO的主要创新在于将制造知识作为约束嵌入到强化学习框架中,确保生成的路径既符合设计要求又具备可制造性。

关键设计:在路径优化中,使用三次Hermite插值生成曲率和扭转轮廓,采用随机探索和阶段引导奖励机制来提高优化效率。

📊 实验亮点

实验结果表明,FPRO生成的路径在几何轮廓上更平滑且无碰撞,相较于传统的笛卡尔方法,路径优化在终端对齐、路径长度、障碍物规避和可制造性方面表现出显著提升,收敛速度更快,性能更优。

🎯 应用场景

该研究的潜在应用领域包括航空发动机的管道设计与制造,能够有效提高设计的可制造性和生产效率。未来,该框架可扩展至其他复杂组件的设计与制造过程,推动智能制造的发展。

📄 摘要(原文)

Design for manufacturing plays a critical role in advanced aeroengine development, where complex components necessitate careful consideration of manufacturability. However, current practices in pipe routing remain largely decoupled from down-stream manufacturing, leading to labor-intensive, trial-and-error iterations to achieve manufacturable designs. To address this problem, this study proposes the Frenet-based pipe routing optimization (FPRO) framework, a manufacturability knowledge-integrated reinforcement learning approach for free-form pipe design in aeroengines. FPRO formulates the routing problem as a boundary value problem in the Frenet frame. In this framework, the pipe path is represented by curvature and torsion profiles, which are generated using cubic Hermite interpolation. To integrate design and manufacturing, domain-specific manufacturing knowledge is embedded as constraints on the permissible ranges of curvature and torsion. The path optimization is performed using the proximal policy optimization algorithm with stochastic exploration and a stage-guided reward mechanism. A unified mapping formulation then translates the optimized path into motion trajectories for the bending die, enabling direct fabrication on a six-axis free-bending machine. Experimental results demonstrate that FPRO consistently generates collision-free, manufacturable paths with smoother geometric profiles compared to Cartesian-based methods. It also achieves faster convergence and superior performance in terminal alignment, path length, obstacle avoidance, and manufacturability compared to state-of-the-art reinforcement learning baselines. Real-world validation confirms the close geometric correspondence between the manufactured pipe and its digital design, validating the practical feasibility of FPRO.