Fault Diagnostic and Reconfiguration System for Mulitlevel Inverter Drives using Artificial Intelligent based Techniques
Dr. Leon M. Tolbert
A fault diagnostic and reconfiguration system in a multilevel inverter drive (MLID) using a principal component neural network is proposed in this dissertation. Output phase voltages of a MLID can be used as valuable information to diagnose faults and their locations. It is difficult to diagnose a MLID system using a mathematical model because MLID systems consist of many switching devices and their system complexity has a nonlinear factor. Therefore, a neural network (NN) classification is applied to the fault diagnosis of a MLID system. Multilayer perceptron (MLP) networks are used to identify the type and location of occurring faults. The principal component analysis (PCA) is utilized in the feature extraction process to reduce the NN input size. A lower dimensional input space will also usually reduce the time necessary to train a NN, and the reduced noise may improve the mapping performance. The genetic algorithm is also applied to select the valuable principal components. The comparison among MLP neural network (NN), principal component neural network (PC-NN), and genetic algorithm based selective principal component neural network (PC-GA-NN) are performed. Proposed networks are evaluated with simulation test set and experimental test set. The PC-NN has improved overall classification performance from NN by about 5% points, whereas PC-GA-NN has better overall classification performance from NN by about 7.5% points. Therefore, the application of genetic algorithm improves the classification from PC-NN by about 2.5% point. The overall classification performance of the proposed networks is more than 90%.
A reconfiguration technique is also proposed. The effects of using the proposed reconfiguration technique at high modulation index are addressed. The proposed system is validated with experimental results. The proposed fault diagnostic system requires about 6 cycles to clear an open circuit or short circuit fault. The experimental results show that the proposed system performs satisfactorily to detect the fault type, fault location, and reconfiguration.
Related publications and presentations
B. Ozpineci, Z. Du, L. M. Tolbert, D. J. Adams, D. Collins,
“Integrating Multiple Solid Oxide Fuel Cell Modules,”
IEEE Industrial Electronics Conference,
November 2-6, 2003, Roanoke Virginia.
L. M. Tolbert, F. Z. Peng,
"Multilevel Converters as a Utility Interface for Renewable Energy Systems,"
IEEE Power Engineering Society Summer Meeting,
July 15-20, 2000, Seattle, Washington, pp. 1271-1274.