Computer Vision for DC Partial Discharge Diagnostics in Traction Battery Systems

The tendency towards thin insulation layers in traction battery systems presents new challenges regarding insulation quality and service life. Phase-resolved DC partial discharge diagnostics can help to identify defects. Furthermore, different root causes are characterized by different patterns. However, to industrialize the procedure, there is the need for an automatic pattern recognition system. This paper shows how methods from computer vision can be applied to DC partial discharge diagnostics. The derived system is self-learning, needs no tedious manual calibration, and can identify defects within a matter of seconds. Thus, the combination of computer vision and phase-resolved DC partial discharge diagnostics provides an industrializable system for detecting insulation faults and identifying their root causes.