Degradation modeling and remaining useful life prediction method for operational amplifiers using the GA-optimized SVR.

Saved in:

Bibliographic Details
Title:	Degradation modeling and remaining useful life prediction method for operational amplifiers using the GA-optimized SVR.
Authors:	Huang, Xin^1,2 (AUTHOR), Zeng, Ying^1,2 (AUTHOR), Li, Jing^1,2 (AUTHOR), Zhou, Zhenwei³ (AUTHOR), Huang, Hong-Zhong^1,2 (AUTHOR) hzhuang@uestc.edu.cn
Source:	Journal of Mechanical Science & Technology. Jul2025, Vol. 39 Issue 7, p3599-3607. 9p.
Subjects:	Remaining useful life, Operational amplifiers, Radial basis functions, Heuristic algorithms, Artificial intelligence
Abstract:	Small samples of performance degradation data are commonly obtained during an accelerated degradation test. This study leverages the global search capabilities of heuristic algorithms to enhance the performance of support vector regression (SVR) in degradation modeling with such constrained data, utilizing genetic algorithms to optimally select model parameters. The life prediction results from the Arrhenius model are used as a benchmark in the kernel function selection in the SVR model. Comparative analysis showed that the sigmoid kernel function demonstrated superior nonlinear mapping capabilities and achieved high prediction accuracy. Furthermore, the radial basis function neural network exhibited poorer generalization performance in scenarios involving small sample sizes compared with other models. [ABSTRACT FROM AUTHOR]
	Copyright of Journal of Mechanical Science & Technology is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Small samples of performance degradation data are commonly obtained during an accelerated degradation test. This study leverages the global search capabilities of heuristic algorithms to enhance the performance of support vector regression (SVR) in degradation modeling with such constrained data, utilizing genetic algorithms to optimally select model parameters. The life prediction results from the Arrhenius model are used as a benchmark in the kernel function selection in the SVR model. Comparative analysis showed that the sigmoid kernel function demonstrated superior nonlinear mapping capabilities and achieved high prediction accuracy. Furthermore, the radial basis function neural network exhibited poorer generalization performance in scenarios involving small sample sizes compared with other models. [ABSTRACT FROM AUTHOR]
ISSN:	1738494X
DOI:	10.1007/s12206-025-2404-6