arXiv cs.AI· F\'elix Martinez-Jim\'enez (GIPSA-INFINITY), Sander Miller-Murphy (GIPSA-INFINITY), Tobie Ondoa-Essomba (GIPSA-INFINITY), Emmanuel Witrant (GIPSA-INFINITY)·· 3 小时前AI 评分32
带偏梯度的迭代反馈调参：电子节气门阀上无模型控制的 IFT 调优研究
Learning to Tune with Biased Gradients: Iterative Feedback Tuning of Model-Free Control on Throttle Valves
AI 导读
arXiv 论文研究迭代反馈调参（IFT）在汽车电子节气门阀上的应用，其梯度估计仅对线性对象无偏，而阀间摩擦与静摩擦差异会引入与第二次实验幅值成反比的误差。在 10 个数字孪生阀上，IFT 梯度仅在 69% 的低成本区域为下降方向，且各更新规则均先平台化后漂移；在两个硬件阀上，Adam 与 Gauss-Newton 的最优选择取决于梯度噪声结构，数字孪生能复现机制但无法复现该排序。
正文 · 原文
Abstract:Iterative feedback tuning (IFT) learns the parameters of a fixed-structure controller by stochastic gradient descent. At each iteration, two closed-loop experiments are run on the plant: the first one measures the tracking error, and the second one, driven by this error, provides the sensitivities from which the gradient of the cost is estimated. This estimate is unbiased for linear plants only. We study the biased case on automotive electronic throttle valves, whose friction and stiction vary between valves and runs, controlled by an intelligent proportional (model-free) controller, which is an incremental PI controller. We show that the mismatch of the controller state at the start of the two experiments, which stiction makes unavoidable, adds an error inversely proportional to the amplitude of the second experiment. On digital twins of ten valves, the IFT gradient is a descent direction in only 69\% of the low-cost region, friction being the cause, and all update rules plateau and then drift. On two hardware valves, the best update rule depends on the noise structure of the gradient. On the first valve, where one gradient component is buried in noise, Adam outperforms Gauss--Newton, its normalisation and its momentum each improving one parameter. On the second valve, where both components are consistent, the same normalisation amplifies a direction that Gauss--Newton rightly discounts, and Adam drifts to a controller worse than the initial one. The twins reproduce the mechanism but not this ranking.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.06338 [cs.LG] |
| (or arXiv:2611.06338v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06338 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Emmanuel Witrant [view email] [via CCSD proxy]
[v1]
Wed, 4 Nov 2026 11:01:04 UTC (145 KB)
来源：arXiv cs.AI · arxiv.org