Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 20, 2026Energy Conversion and EconomicsOpen Access

State of health estimation for lithium‐ion batteries using modern heuristic algorithm optimized multiple kernel extreme learning

View Full Paper
Ask AI
Bookmark
Share

Authors

YZYumin ZhangYLYongtao LiuPYPing Ye

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved state of health estimation in lithium-ion batteries, suggesting better monitoring in real-world usage.

Key Points

  • The aim is to develop an improved framework for estimating the state of health (SOH) of lithium-ion batteries, focusing on non-linear degradation.
  • Proposed a data-driven SOH estimation framework using indirect health indicators extracted from operational data.
  • Used a hybrid multiple kernel extreme learning machine with various kernel types to model battery degradation.
  • Developed a grey wolf optimizer to optimize hyperparameters and improve the performance of the estimation model.
  • Validation shows the GRGWO-HMKELM framework estimates SOH accurately using early-cycle data, outperforming baseline models.
  • Indicates superior generalization for in-service monitoring, enhancing safety and reliability in battery operation.

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/6a362f92db0793dc1a537085https://doi.org/10.1049/enc2.70041
View Full Paper
Ask AI
Bookmark
Share