arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2607.06459eess.SYcs.SY
收藏

通过投影残差对非线性重复系统的柯普曼学习控制进行输入到状态稳定性认证

Input-to-State Stability Certification via Projection Residuals for Koopman Learning Control of Nonlinear Repetitive Systems

School of Automation, Xi’an Jiaotong University(西安交通大学自动化学院);Xinjiang Cigarette Factory, Hongyun Honghe Tobacco (Group) Co., Ltd.(新疆卷烟厂,红云红河烟草(集团)有限责任公司)

Yue Wu, Ye Cao, Jianfu Cao

AI总结:

研究未知离散时间非线性重复系统数据驱动柯普曼学习控制的输入到状态稳定性认证,通过将堆叠跟踪误差设为系统状态,考虑多种因素为ISS输入,给出确定性结果与有限样本实现,数值检验支持相关特性。

摘要:

本文研究了未知离散时间非线性重复系统在有限试验范围内数据驱动的柯普曼学习控制的输入到状态稳定性(ISS)认证。我们不是提出新的学习律,而是验证固定的柯普曼辅助约束更新何时能使所选跟踪误差沿试验轴具有实际稳定性。仅预测精度不足以实现此目的:所选有限时域输入输出通道必须有正裕度,且请求输出增量的不可达分量必须通过投影残差来考虑。因此,如果所选通道较弱,具有小的留出预测残差的柯普曼预测器仍可能无法通过学习稳定性认证。我们将所选的堆叠跟踪误差公式化为离散时间学习轴系统的状态,并将柯普曼残差、重置失配、通道不确定性、投影残差、部署偏移和数值容差视为ISS输入。确定性结果给出了从初始学习误差到明确最终带的实际ISS估计。有限样本实现构建了固定控制器下的情节级残差界,并将其与报告的通道、投影、偏移和数值裕度相结合。对非线性重复系统的数值检验支持了预测的残差到带的缩放、弱通道抑制、投影闭合和最终带覆盖。

英文摘要:

This paper studies input-to-state stability (ISS) certification for data-driven Koopman learning control of unknown discrete-time nonlinear repetitive systems over finite trial horizons. Rather than proposing a new learning law, we certify when a fixed Koopman-assisted constrained update yields practical stability of the selected tracking error along the trial axis. Prediction accuracy alone is insufficient for this purpose: the selected finite-horizon input-output channel must have a positive margin, and the unreachable component of the requested output increment must be accounted for through a projection residual. Thus, a Koopman predictor with small held-out prediction residuals may still fail the learning-stability certificate if its selected channel is weak. We formulate the selected stacked tracking error as the state of a discrete-time learning-axis system and treat Koopman residuals, reset mismatch, channel uncertainty, projection residuals, deployment shifts, and numerical tolerances as ISS inputs. The deterministic result gives a practical ISS estimate from the initial learning error to an explicit ultimate band. A finite-sample implementation constructs an episode-level residual bound under a fixed controller and combines it with reported channel, projection, shift, and numerical margins. Numerical checks on nonlinear repetitive systems support the predicted residual-to-band scaling, weak-channel rejection, projection closure, and ultimate-band coverage.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑