Nondestructive Magnetisation Estimation for Permanent Magnets Using Autoencoder-Based Dimensionality Reduction

IF 1.3 4区工程技术 Q3 ENGINEERING, ELECTRICAL & ELECTRONIC

Iet Science Measurement & Technology Pub Date : 2025-08-20 DOI:10.1049/smt2.70024

Kazuki Igarashi, Hidenori Sasaki

引用次数: 0

Abstract

A magnetisation estimation method that uses an autoencoder (AE) model with a convolutional neural network (CNN) is proposed. The proposed method achieved high accuracy even for complex magnetisation distributions, including defective regions. The proposed model improved estimation accuracy by over 50.62% compared to the conventional multi-layer perceptron method. Additionally, the proposed model is effective for multi-output regression problems involving multidimensional vectors. This method enables non-destructive and rapid estimation of internal magnetisation in permanent magnets from external magnetic flux density.

Abstract Image

查看原文本刊更多论文

基于自编码器的永磁体无损磁化降维估计

提出了一种基于卷积神经网络（CNN）的自编码器（AE）模型的磁化估计方法。所提出的方法即使在复杂的磁化分布（包括缺陷区域）中也具有很高的精度。与传统的多层感知器方法相比，该模型的估计精度提高了50.62%以上。此外，该模型对于涉及多维向量的多输出回归问题是有效的。这种方法可以从外部磁通密度非破坏性地快速估计永磁体的内部磁化。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Iet Science Measurement & Technology 工程技术-工程：电子与电气

CiteScore

4.30

自引率

7.10%

发文量

审稿时长

7.5 months

期刊介绍： IET Science, Measurement & Technology publishes papers in science, engineering and technology underpinning electronic and electrical engineering, nanotechnology and medical instrumentation.The emphasis of the journal is on theory, simulation methodologies and measurement techniques. The major themes of the journal are: - electromagnetism including electromagnetic theory, computational electromagnetics and EMC - properties and applications of dielectric, magnetic, magneto-optic, piezoelectric materials down to the nanometre scale - measurement and instrumentation including sensors, actuators, medical instrumentation, fundamentals of measurement including measurement standards, uncertainty, dissemination and calibration Applications are welcome for illustrative purposes but the novelty and originality should focus on the proposed new methods.