System and method for determining harmonic contributions from non-linear loads

Neural networks have been known to be good function approximators. They are particularly effective in dealing with non-linear relationships between parameters. This feature is exploited in this paper to propose a new method for the problem of measuring harmonic current injected into a power system network by a non-linear load without disconnecting the load from the network. This work is particularly useful in determining whether the utility or the customer side has a higher contribution to harmonic pollution in a network. Hence this method would be helpful in settling utility-customer disputes over who is responsible for harmonic distortions. The main advantage of this method is that only waveforms of voltages and currents have to be measured. A neural network structure with memory is used to identify or learn the non-linear load admittance of a load. Once it has learned the admittance, the neural network predicts the true harmonic current of the load when supplied with a clean sine wave. This method is applicable for both single and three phase loads. This could be fabricated into a commercial instrument that could be installed in substations of large customer loads, or used as a hand-held clip on instrument.