An independent component analysis based correlation coefficient method for internal short-circuit fault diagnosis of battery-powered intelligent transportation systems

Abstract

Battery-powered intelligent transportation systems (BPITS) are growing at an alarming rate, and a problem that cannot be ignored is that the safety of battery packs is currently the weak link in the security of BPITS. However, developing a fast and reliable diagnostic method is not easy due to the large number of battery cells and the difficulty to guarantee consistency among the individual cells. To better resolve this problem, a new fault diagnosis scheme based on voltage correlation coefficient (VCC) and independent component analysis (ICA) model is proposed in this paper. Where VCC is used to extract the fault signature of the battery pack independent of the cell inconsistency; and ICA is used to model the non-Gaussian distributed high-dimensional VCC signals in parallel and derive a statistical-based fault detection index. The kernel density estimation-based algorithm is used to calculate the theoretical threshold and to determine the optimal window width for VCC. In particular, a variable reconstruction-based fault isolation algorithm is proposed for accurate and reliable determination of the location of the faulty cell to prevent the smearing effect. Experimental results conducted on a real battery testbed under different conditions and configurations show that the new method provides significant improvements in both detection latency and positioning reliability in diagnosing internal short-circuit (ISC) faults with different failure grades.