Fault Diagnostic System for Cascaded H-Bridge Multilevel Inverter ...
Fault Diagnostic System for Cascaded H-Bridge Multilevel Inverter ...
Fault Diagnostic System for Cascaded H-Bridge Multilevel Inverter ...
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
All occurring fault features can be classified based on their effects of the output voltages;<br />
<strong>for</strong> that reason, one can use the output voltage signals as learning/training data to a neural<br />
network. A neural network has the ability to recognize anomalous situations because of<br />
their intrinsic capacity to classify and generalize. Genetic algorithm and principal<br />
component analysis can also be applied in feature extraction process in order to rate<br />
signals as an important feature. Thus, by applying the proposed AI-based techniques in a<br />
fault diagnostic system, a better understanding on fault behaviors, detections, and<br />
reconfigurations of a multilevel inverter drive system can be accomplished.<br />
1.7 Organization of the dissertation<br />
Chapter 2 provides a survey of previous works. Several approaches from previous<br />
research related in fault diagnosis, detection, and reconfiguration methods are<br />
investigated in this chapter. The proposed fault diagnostic and detection techniques <strong>for</strong> a<br />
multilevel inverter by using a neural network are described in chapter 3. Chapter 3 also<br />
provides the procedure of how to apply the AI techniques to fault diagnosis and<br />
detection. Reconfiguration techniques are introduced and examined in chapter 4. Chapter<br />
5 illustrates the software and hardware implementation of an experiment test rig to<br />
validate the proposed fault diagnosis system. Finally, conclusions and recommendations<br />
<strong>for</strong> future work are discussed in chapter 6.<br />
18