面向半导体晶圆厂物料控制系统的学习辅助拥塞感知路径调度
Learning-Assisted Congestion-Aware Route Scheduling for Semiconductor Fab Material Control Systems
- The University of Hong Kong（香港大学）
- Tsinghua University（清华大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对半导体晶圆厂物料控制系统的路径调度问题，提出TN-DCR表示与风险约束调度规则，经评估可降低交付与等待时间且保持吞吐量不变。
AI中文摘要：
半导体晶圆厂中的自动化物料搬运系统由物料控制系统（MCS）运行，该系统必须在线为每个运输命令调度中继路径，且需在执行前完成。这是一个数据驱动的调度问题，其中路径成本的上尾部分主要由异构、部分可观测的中继设备排队决定，因此路径选择需要在决策时刻同时估计交付时间和拥塞风险。本文提出一种感知运输网络的动态拥塞表示（TN-DCR），其基于历史观测到的中继段诱导的静态有向运输图构建，结合了结构路径先验、多窗口全网拥塞上下文、路径级瓶颈暴露以及归纳式图感知路径嵌入，所有组件均在预测时间安全不变性下构建，仅采用预测时刻之前严格观测到的信息。该表示输入两个独立的排队时间和转移时间回归器，以及一个序数多标签分类器，该分类器生成校准后的多阈值超出分数，同时采用经验贝叶斯库存键残差校正以减少系统的排队时间低估。这些预测作为风险约束路径调度规则中的成本，该规则在极端拥塞概率受限的条件下最小化预测交付时间，将学习到的预测器嵌入轻量级运筹学决策模型中。在受控闭环评估中，平均交付时间降低16.4%，内部资源等待时间降低22.6%，而吞吐量基本保持不变。
英文摘要：
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.
