用动态拥堵表征优化晶圆厂物流路径，降低16%交付时延。
Learning-Assisted Congestion-Aware Route Scheduling for Semiconductor Fab Material Control Systems
- 构建基于历史路径的动态拥堵表示，融合网络上下文与瓶颈暴露信息。
- 交付时延减少16.4%，内部等待时间下降22.6%，吞吐量基本不变。
- 适合晶圆厂自动化调度系统研发与运维人员参考。
半导体晶圆厂的自动物料搬运系统由物料控制系统（MCS）实时调度每条运输指令的路径。该问题具有数据驱动特性，路径成本主要受异构、部分可观测的中继设备队列影响，因此路径选择需在决策时刻估计交付时间和拥堵风险。本文提出一种运输网络感知的动态拥堵表征（TN-DCR），基于历史观测的有向运输图构建，结合路径先验、多窗口全局拥堵上下文、路径级瓶颈暴露及归纳式图感知嵌入，所有信息均满足预测时间安全约束，仅使用预测时刻前可观察数据。该表征输入独立的队列与转运时间回归器及有序多标签分类器，生成校准的多阈值超限评分，并通过经验贝叶斯库存关键残差修正系统性队列时间低估。预测结果作为风险约束路径调度规则中的代价，最小化预测交付时间的同时控制极端拥堵概率，嵌入轻量级运筹学决策模型。在闭环测试中，平均交付时延降低16.4%，内部资源等待时间减少22.6%，吞吐量几乎不变。
原文摘要 · Abstract (English)
Automated material handling systems in semiconductor fabs are operated by a material control system (MCS) that must schedule a relay route for every transport command online, before execution. This is a data-driven scheduling problem in which route cost is dominated in the upper tail by queueing at heterogeneous, partially observable relay equipment, so route selection requires estimating both delivery time and congestion risk at the decision moment. This paper proposes a transport-network-aware dynamic congestion representation (TN-DCR). Built on a static directed transport graph induced by historically observed relay segments, TN-DCR combines structural route priors, multi-window network-wide congestion context, route-level bottleneck exposure, and an inductive graph-aware route embedding, all constructed under a prediction-time-safety invariant that admits only information observed strictly before the prediction moment. The representation feeds separate queue- and transfer-time regressors and an ordinal multi-label classifier producing calibrated multi-threshold exceedance scores, with an empirical-Bayes stock-key residual correction reducing systematic queue-time underprediction. The predictions serve as costs in a risk-constrained route-scheduling rule that minimizes predicted delivery time subject to a bound on extreme-congestion probability, embedding the learned predictors within a lightweight operations-research decision model. In a controlled closed-loop evaluation, mean delivery time falls by 16.4\% and internal resource waiting time by 22.6\% while throughput remains essentially unchanged.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。