August 12, 2025

Permanent magnet temperature prediction model based on improved multi-head attention and enhanced loss function

View Full Paper

Ask AI

Bookmark

Authors

FGFuyan Guo FDFei Dong YWYue WangChina Telecom (China)

Discussion

Member takes

Implication

A novel model combines multi-head attention and an enhanced loss function to improve temperature prediction in synchronous motors, suggesting better performance during abrupt changes.

Key Points

The MSNB-EMSE-LI model significantly reduces mean absolute error compared to traditional models, enhancing prediction accuracy for permanent magnet temperatures.
Experimental results demonstrate a noticeable reduction in root mean squared error, validating the model's potential for robust temperature management in electric vehicle motors.
Key innovations include an improved nonlinear function to better model complex relationships among variables, and an enhanced loss function to handle sudden temperature changes effectively.
The approach highlights the importance of accurately capturing spatio-temporal dependencies for reliable operation of permanent magnet synchronous motors.

Cite This Study

Guo et al. (2025) studied this question.

synapsesocial.com/papers/68c23595b210217d6477109e https://doi.org/10.21203/rs.3.rs-7094948/v1

View Full Paper

Ask AI

Bookmark

Implication

A novel model combines multi-head attention and an enhanced loss function to improve temperature prediction in synchronous motors, suggesting better performance during abrupt changes.

Permanent magnet temperature prediction model based on improved multi-head attention and enhanced loss function

Discussion

Member takes

Implication

Key Points

Cite This Study

Permanent magnet temperature prediction model based on improved multi-head attention and enhanced loss function

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider