Application of chaos and extension theory to fault diagnosis of three-phase synchronous generators

Abstract

This study applied an extension algorithm combined with the Chaos Theory to the fault diagnosis of the three-phase synchronous generator. First, the three-phase synchronous generator is classified, including normal, carbon brush fault, three-phase unbalance, and insulation deterioration, and then by means of hardware measurement circuit and device, electrical signals are measured for each category and a chaotic error scatter map is built through the Chaos Theory to get the chaotic eye coordinates under specific fault categories. Next, the extension algorithm is used to carry out the correlation function and the normalization calculation, evaluating the type of fault to which it belongs. The analysis results show that the proposed method can effectively identify the fault types of three-phase synchronous generators and significantly reduce the amount of feature extraction data, so as to effectively detect the change of fault signals, allowing us to know the operation state of three-phase synchronous generators.

Fault Diagnosis of Wind Turbine Blades Based on Chaotic System and Extension Neural Network

“…This method has often been applied to fault signal feature extraction. (10,11) Chaos theory was proposed by Edward Norton Lorenz, an American meteorologist, and the chaos phenomenon is a characteristic of nonlinear systems. We utilize the chaotic system of Lorenz for system feature extraction.…”