Diagnosis of a battery energy storage system based on principal component analysis

Abstract

This paper proposes the use of principal component analysis (PCA) for the state of health (SOH) diagnosis of a battery energy storage system (BESS) that is operating in a renewable energy laboratory located in Chocó, Colombia. The presented methodology allows the detection of false alarms during the operation of the BESS. The principal component analysis model is applied to a parameter set associated to the capacity, internal resistance and open circuit voltage of a battery energy storage system. The parameters are identified from experimental data collected daily. The PCA model retains the first 5 components that collect 80.25% of the total variability. During the test under real operation contidions, PCA diagnosed a degradation of state of health fastest than the comercial battery controller. A change in the charging modes lead to a battery recovery that was also monitored by the proposed algortihm, and control actions are proposed that lead the BESS to work in normal conditions.