Published Paper Details:

Solar PV farm used for simulation studies involve of large number of PV module connected to grid connected inverter through ungrounded DC cables. Constructor report that about 1% of installed PV panel fails annually. Detecting phase to ground fault in ungrounded underground DC cables is also difficult and time consuming .therefore Identifying ground faults is a important problem in ungrounded photovoltaic (PV) systems because such earth faults do not provide abundant fault currents for their detection and location during system working. If such ground faults are not cleared rapidly, a subsequent ground fault on the healthy phase will produce a complete short circuit in the system. This paper present a novel fault-location scheme in which high frequency noise patterns are used to identify the fault location. The high-frequency noise is produce due to the switching transients of converters combined with the parasitic capacitance of PV panels and cables. Discrete wavelet transform is used for the decomposition of the monitored signal (midpoint voltage of the converters) and features are taken out. Feature extraction of the measured waveform at different frequency bands give feature information of voltage signal at different fault locations and are used as the feature vectors for pattern recognition. Then, a back propagation artificial neural networks classifier, which can automatically classify the fault locations according to the extracted features, is investigated. The proposed fault-location scheme has been primarily expand for fault location in the PV farm (PV panels and dc cables). The method is assessing for ground faults as well as line� line faults. These faults are simulated with MATLAB and the data are then analyzed with wavelets. Finally, the value of the designed fault locator is tested with varying system parameters. The results illustrate that the proposed approach has accurate and robust performance even with noisy measurements and changes in operating conditions.