arXiv cs.AI· Perceval Beja-Battais (CB), Alain Grosset{\^e}te (CB), Nicolas Vayatis (CB)·· 2 小时前AI 评分37
SRLBC 行为克隆加速非线性 MPC：应用于核反应堆负荷跟踪
Accelerating Nonlinear MPC by Behavior Cloning with Separated Timescales: Application to Nuclear Reactor Load-Following
AI 导读
研究提出结构化表示学习行为克隆方法 SRLBC，利用慢变量、快变量和外生输入的时间尺度分离来克隆专家控制器。在压水堆负荷跟踪基准的 500 个长时程 roll-out 和 20 个训练种子上，分离嵌入在累计成本、模仿精度和约束满足上系统性优于共享嵌入基线；独立策略闭环性能接近 NMPC，平均计算成本低 15 倍。
正文 · 原文
Abstract:Behavior Cloning (BC) of expert controllers for multiscale dynamical systems is challenging: state variables evolving at widely separated timescales induce highly nonlinear couplings that a shared latent space may fail to adequately represent, degrading closed-loop generalization. We propose Structured Representation Learning for Behavior Cloning (SRLBC), an architecture designed to leverage the physical knowledge of multiscale systems in which slow state variables, fast (stiff) state variables, and predictable exogenous inputs evolve at different timescales. On 500 long-horizon roll-outs of a pressurized water reactor (PWR) load-following benchmark -a high-dimensional, stiff industrial system with challenging safety constraints -and across 20 training seeds, separated embeddings systematically outperform shared embedding baselines on cumulative cost, imitation accuracy and constraint satisfaction. The resulting standalone policies approach NMPC closed-loop performance at a computational cost 15 times lower on average. Since standalone policies still leave a few percent of trajectories infeasible, we embed the learned policies in a safety-augmented approximate NMPC framework, in which the optimizer is only called when the predicted input sequence is not certified as safe. This yields controllers still 6.8 times faster than the NMPC controller on average, with a feasibility (i.e., constraint satisfaction) of at least 99.8% for all architectures, SRLBC retaining the lowest closed-loop cost. Under distribution shift, standalone BC policies degrade sharply: SRLBC degrades the least, and once safety-augmented, it retains a feasibility above 98% with the lowest closed-loop cost. Beyond the quantitative results, Jacobian-based sensitivity analysis shows that the resulting controller relies on a sparse and less redundant set of latent features, each attributable to a single group of physical variables, and aligned with the physical timescale decomposition of the system.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Optimization and Control (math.OC) |
| Cite as: | arXiv:2610.38496 [cs.AI] |
| (or arXiv:2610.38496v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.38496 arXiv-issued DOI via DataCite |
Submission history
From: Perceval Beja-Battais [view email] [via CCSD proxy]
[v1]
Wed, 28 Oct 2026 09:15:18 UTC (337 KB)
来源：arXiv cs.AI · arxiv.org