arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.03741eess.SYcs.SY
收藏

NARX结构离散前馈神经网络的稳定性

Stability of discrete-time feed-forward neural networks in NARX configuration

Fabio Bonassi, Marcello Farina, Riccardo Scattolini

摘要:

在机器学习应用于非线性系统辨识的早期,由于前馈神经网络(FFNN)结构简单,易于应用于控制设计,因此将其用作非线性自回归外生(NARX)模型的回归函数,从而得到本文中称为神经NARX(NNARX)的模型的思想已经相当流行。尽管如此,很少有理论结果是关于这些模型的稳定性。本文针对这一问题,给出了保证NNARX模型具有输入到状态稳定性(ISS)和增量输入到状态稳定性(δISS)的一个充分条件.这个条件是底层FFNN权重的不等式,可以在训练过程中强制执行,以确保模型的稳定性。所提出的模型,随着这一稳定性条件下,进行了测试的pH值中和过程的基准,显示出令人满意的结果。

英文摘要:

The idea of using Feed-Forward Neural Networks (FFNNs) as regression functions for Nonlinear AutoRegressive eXogenous (NARX) models, leading to models herein named Neural NARXs (NNARXs), has been quite popular in the early days of machine learning applied to nonlinear system identification, owing to their simple structure and ease of application to control design. Nonetheless, few theoretical results are available concerning the stability properties of these models. In this paper we address this problem, providing a sufficient condition under which NNARX models are guaranteed to enjoy the Input-to-State Stability (ISS) and the Incremental Input-to-State Stability (δISS) properties. This condition, which is an inequality on the weights of the underlying FFNN, can be enforced during the training procedure to ensure the stability of the model. The proposed model, along with this stability condition, are tested on the pH neutralization process benchmark, showing satisfactory results.

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。

↑