Loading...
Publication
Fault detection and diagnosis technique for a SRM drive based on a multilevel converter using a machine learning approach
| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 362.29 KB | Adobe PDF |
Advisor(s)
Abstract(s)
SRM drives based on multilevel converters is
now a solution well accepted due to their interesting features
like extended voltage range and capability to fault tolerance.
However, one aspect that is fundamental to ensure fault
tolerance or preventive maintenance is the fault detection and
diagnosis of failures in power semiconductors. In this way, in
this paper it is presented a new diagnostic method for the
failure of those semiconductors in asymmetric neutral point
clamped converters. The proposed method will be based on
the development of specific patterns that are associated to
each semiconductor and fault type. The procedures presented
here are based on the image identification of the currents
patterns in the multilevel converter that allow the
identification of distinct fault type. The pattern recognition
system uses visual-based efficient invariants features for
continuous monitoring of multilevel converter The proposed
method will be verified through several tests in which were
used a simulation tool and an experimental prototype.
Description
Trabalho apresentado em 12th International Conference on Renewable Energy Research and Applications (ICRERA 2023), 29 augusto-1 setembro 2023, Oshawa, Canada
Keywords
Fault Diagnosis Detection, pattern recognition Machine learning SRM Multilevel converters