| Autor: |
An D; Hebei Research Institute of Drug and Medical Device Inspection, Shijiazhuang, 050200., Shi L; Hebei Province Industrial Transformation and Upgrading Service Center, Shijiazhuang, 050000., Xu Y; Hebei Research Institute of Drug and Medical Device Inspection, Shijiazhuang, 050200. |
| Jazyk: |
čínština |
| Zdroj: |
Zhongguo yi liao qi xie za zhi = Chinese journal of medical instrumentation [Zhongguo Yi Liao Qi Xie Za Zhi] 2024 May 30; Vol. 48 (3), pp. 293-297. |
| DOI: |
10.12455/j.issn.1671-7104.230529 |
| Abstrakt: |
The development of portable medical devices cannot be separated from safe and efficient batteries. Accurately predicting the remaining life of batteries can greatly improve the reliability of batteries, which is of great significance for portable medical devices. This article focuses on the high dependence of the BP neural network algorithm on initial weights and thresholds, as well as its tendency to fall into local minima. The Northern Goshawk Optimization (NGO) algorithm is used to optimize the BP neural network and to test the 18650 lithium battery data under different ambient temperatures (4, 24, 43°C) typical of medical equipment. The experimental results show that the NGO algorithm can significantly improve the prediction accuracy of the BP neural network under various temperature conditions, achieving accurate and effective prediction of the remaining battery life. |
| Databáze: |
MEDLINE |
| Externí odkaz: |
|
