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 2409.13654cs.LGmath.DS
收藏

一种提高动态系统神经网络模型精度的新型神经滤波器

A Novel Neural Filter to Improve Accuracy of Neural Network Models of Dynamic Systems

University of Maryland, Baltimore County(马里兰大学巴尔的摩县分校)

Parham Oveissi, Turibius Rozario, Ankit Goel

AI总结:

针对神经网络长期预测误差发散问题,提出一种受扩展卡尔曼滤波启发的神经滤波器,融合状态预测与物理测量,在四个非线性系统上显著提升精度并约束协方差。

摘要:

神经网络由于能够估计复杂的非线性函数,其在动态系统建模中的应用已十分突出。尽管神经网络有效,但在长期预测中仍面临挑战:预测误差会随时间发散,从而降低其精度。本文提出一种神经滤波器,以提高基于神经网络的动态系统模型的长期状态预测精度。受扩展卡尔曼滤波器启发,该神经滤波器将神经网络状态预测与来自物理系统的测量值相结合,以提高估计状态的精度。通过应用于四个非线性动态系统,展示了该神经滤波器在预测精度方面的改进。数值实验表明,该神经滤波器显著提高了预测精度并约束了状态估计协方差,优于神经网络预测。此外,研究还表明,训练不佳的神经网络模型的精度可以提升到与训练充分的神经网络模型相同的水平,这有可能降低训练成本以及训练神经网络所需的数据量。

英文摘要:

The application of neural networks in modeling dynamic systems has become prominent due to their ability to estimate complex nonlinear functions. Despite their effectiveness, neural networks face challenges in long-term predictions, where the prediction error diverges over time, thus degrading their accuracy. This paper presents a neural filter to enhance the accuracy of long-term state predictions of neural network-based models of dynamic systems. Motivated by the extended Kalman filter, the neural filter combines the neural network state predictions with the measurements from the physical system to improve the estimated state's accuracy. The neural filter's improvements in prediction accuracy are demonstrated through applications to four nonlinear dynamical systems. Numerical experiments show that the neural filter significantly improves prediction accuracy and bounds the state estimate covariance, outperforming the neural network predictions. Furthermore, it is also shown that the accuracy of a poorly trained neural network model can be improved to the same level as that of an adequately trained neural network model, potentially decreasing the training cost and required data to train a neural network.

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。

↑