arXiv cs.AI· Caicheng Wang, Zili Wang, Shuyou Zhang, Yongzhe Xiang, Zheyi Li, Jianrong Tan·· 2 天前AI 评分22
基于自学习的航空发动机自由曲面管路自适应布局框架 SLPR
A self-learning framework for adaptive free-form pipe routing in aeroengines
AI 导读
研究提出基于 PPO 的自学习方法 SLPR，用于优化航空发动机自由曲面管路布局，并集成统一规则建模框架与势能表实现连续空间中的障碍检测和模糊规则建模。对比测试显示，SLPR 以三次 NURBS 曲线生成平滑管路，在管路长度、规则遵循度、路径复杂度和计算效率上均优于三个代表性基线。在动态设计环境中，SLPR 无需从头搜索，甚至优于重新训练的模型。
正文 · 原文
Abstract:Pipe routing is a highly complex, time-consuming, and no-deterministic polynomial-time hard (NP-hard) problem in aeroengine design. Despite extensive research efforts in optimizing constant-curvature pipe routing, the growing demand for free-form pipes poses new challenges. Dynamic design environments and fuzzy layout rules further impact the optimization performance and efficiency. To tackle these challenges, this study proposes a self-learning-based method (SLPR) for optimizing free-form pipe routing in aeroengines. The SLPR is based on the proximal policy optimization (PPO) algorithm and integrates a unified rule modeling framework for efficient obstacle detection and fuzzy rule modeling in continuous space. Additionally, a potential energy table is constructed to enable rapid queries of layout tendencies and interference. The agent within SLPR iteratively refines pipe routing and accumulates the design knowledge through interaction with the environment. Once the design environment shifts, the agent can swiftly adapt by fine-tuning network parameters. Comparative tests reveal that SLPR ensures smooth pipe routing through cubic non-uniform B-spline (NURBS) curves, avoiding redundant pipe segments found in constant-curvature pipe routing. Results in both static and dynamic design environments demonstrate that SLPR outperforms three representative baselines in terms of the pipe length reduction, the adherence to layout rules, the path complexity, and the computational efficiency. Furthermore, tests in dynamic environments indicate that SLPR eliminates labor-intensive searches from scratch and even yields superior solutions compared to the retrained model. These results highlight the practical value of SLPR for real-world pipe routing, meeting lightweight, precision, and sustainability requirements of the modern aeroengine design.
| Comments: | Accepted for publication in SCIENCE CHINA Technological Sciences |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Systems and Control (eess.SY) |
| ACM classes: | J.0; J.6 |
| Cite as: | arXiv:2504.03669 [cs.LG] |
| (or arXiv:2504.03669v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2504.03669 arXiv-issued DOI via DataCite |
|
| Journal reference: | Sci. China Technol. Sci. 69, 1720402 (2026) |
| Related DOI: | https://doi.org/10.1007/s11431-025-3256-9
DOI(s) linking to related resources |
Submission history
From: Caicheng Wang [view email]
[v1]
Thu, 20 Mar 2025 13:45:13 UTC (4,076 KB)
[v2]
Thu, 15 Oct 2026 08:48:47 UTC (2,598 KB)
来源：arXiv cs.AI · arxiv.org