Enhanced DC-link Capacitors Failure Diagnosis for a Three-Phase Interleaved Converter, Using Hilbert Transform

Aluminum electrolytic capacitors (AECs) play a crucial role in power converters, yet they are notably prone to failures. Consequently, there is an urgent need to develop fault diagnosis techniques (FDTs) to assess the AECs health status during converter operation. As AECs age their equivalent series resistance (ESR) increase. Consequently, ESR is commonly used as an indicator to evaluate the AECs health status. This paper proposes a solution that eliminates the need for sensor integration in the converter and is particularly resilient to transients, addressing two common issues in FDTs design. Hence, in a first moment, the proposed FDT employs two 4th order Butterworth filters to extract the capacitor voltage and current waveform modes. Afterwards, it uses the Hilbert transform to extract the envelopes of each signal mode. Finally, the ESR estimate is derived from a simple analytical relationship. In order to reduce oscillation resulting from the initial estimate, an average filter is applied. The proposed approach is particularly suited for applications employing the three-phase Interleaved Boost Converter (IBC) architecture, offering a context-specific solution tailored to the intricacies of this converter topology.