Pioneering CPMI framework for accurate state-of-health assessment in Lithium ion battery power management using FBG sensors

Abstract

Continuous monitoring of the State of Health (SOH) in Lithium-ion (Li-ion) batteries is crucial for ensuring operational reliability and safety in powered devices. This paper presents a novel Classifier-Pursued Maintenance Index Scheme (CPMI) that leverages Fiber Bragg Grating (FBG) sensor measurements for sustainable SOH monitoring and maintenance scheduling. The CPMI framework processes real-time temperature and strain measurements from strategically placed FBG sensors during charge-discharge cycles to estimate battery capacity degradation and determine maintenance requirements. The proposed system employs a support vector-based classification algorithm that categorizes operational states based on FBG sensor data streams, identifying deviations from optimal temperature and voltage ranges. This classification approach generates a quantitative maintenance index that enables systematic assessment scheduling rather than arbitrary inspections. Experimental validation over 200 charge-discharge cycles demonstrates the CPMI system's effectiveness, achieving a maintenance state identification accuracy of 0.95, 75 % classification success rate, classification latency of 0.1 s, precision exceeding 0.95, and an assessment reliability of 0.98. Integrating FBG sensors with the CPMI framework provides a robust Li-ion battery SOH monitoring solution, enabling predictive maintenance strategies and enhanced power management capabilities. The proposed system demonstrates significant potential for improving battery lifecycle management and operational reliability in various applications.