4.6 Article

Learning-Based Approaches to Current Identification from Magnetic Sensors

期刊

SENSORS
卷 23, 期 8, 页码 -

出版社

MDPI
DOI: 10.3390/s23083832

关键词

electromagnetic inverse problems; regularization; machine learning; neural networks; measurement uncertainty

向作者/读者索取更多资源

Direct measurement of electric currents can be difficult, so magnetic sensors are used to estimate the currents based on the measured magnetic fields nearby. However, this approach is classified as an Electromagnetic Inverse Problem (EIP), and careful treatment of the sensor data is required to obtain accurate current measurements. This paper proposes a systematic study of different learning parameters and regularization techniques for accurately reconstructing EIP models. Both traditional methodologies and neural approaches are described and compared in the study.
Direct measurement of electric currents can be prevented by poor accessibility or prohibitive technical conditions. In such cases, magnetic sensors can be used to measure the field in regions adjacent to the sources, and the measured data then can be used to estimate source currents. Unfortunately, this is classified as an Electromagnetic Inverse Problem (EIP), and data from sensors must be cautiously treated to obtain meaningful current measurements. The usual approach requires using suited regularization schemes. On the other hand, behavioral approaches are recently spreading for this class of problems. The reconstructed model is not obliged to follow the physics equations, and this implies approximations which must be accurately controlled, especially if aiming to reconstruct an inverse model from examples. In this paper, a systematic study of the role of different learning parameters (or rules) on the (re-)construction of an EIP model is proposed, in comparison with more assessed regularization techniques. Attention is particularly devoted to linear EIPs, and in this class, a benchmark problem is used to illustrate in practice the results. It is shown that, by applying classical regularization methods and analogous correcting actions in behavioral models, similar results can be obtained. Both classical methodologies and neural approaches are described and compared in the paper.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据