System and method for determining harmonic contributions from non-linear loads without disconnecting any load

A system that determines harmonics caused by non-linear loads, comprising:

• an artificial neural network configured to receive information corresponding to metered current, to train itself such that a predicted voltage determined from the information corresponding to metered current converges with a metered voltage, and to determine a harmonic voltage component using a plurality of weights determined when the predicted voltage converges with the metered voltage wherein a sinusoidal wave is computationally combined with the plurality of determined weights to determine the harmonic voltage component;
• a summing circuit that compares the determined predicted voltage and the metered voltage, and that outputs a voltage error to the artificial neural network such that when the voltage error is less than a predefined threshold, the artificial neural network determines the predicted voltage converges with the metered voltage;
• and
• a processor configured to execute the artificial neural network.

A system for determining harmonics caused by non-linear loads, comprising:

• means for receiving metered voltage from an electric power system;
• means for receiving metered current from the electric power system;
• means for determining a predicted voltage based upon the metered current;
• means for comparing the predicted voltage with the metered voltage;
• means for determining when the predicted voltage converges with the metered voltage by comparing the predicted voltage with the metered voltage;
• means for determining a plurality of weights when the predicted voltage converges with the metered voltage;
• and
• means for determining a harmonic voltage component using the plurality of determined weights, where a sinusoidal wave is computationally combined with the plurality of determined weights to determine the harmonic component.

A computer-readable medium embodying a program executable by a processor circuit for determining harmonics caused by non-linear loads, the program comprising:

• logic configured to receive information corresponding to a metered current from an electric power system;
• logic configured to receive information corresponding to a metered voltage on the electric power system;
• logic configured to determine a predicted voltage based upon the metered current;
• logic configured to determine when the predicted voltage converges with the metered voltage by comparing the predicted voltage with the metered voltage;
• logic configured to determine a plurality of weights when the predicted voltage converges with the metered voltage;
• and
• logic configured to determine a harmonic voltage component using the plurality of determined weights, where a sinusoidal wave is computationally combined with the plurality of determined weights to determine the harmonic component.

An artificial neural network that determines harmonics caused by non-linear loads, comprising:

• a training artificial neural network that determines a predicted voltage from a metered current, and that determines a plurality of weights when the predicted voltage converges with a metered voltage when a voltage error is less than a predefined threshold;
• a comparison circuit that compares the determined predicted voltage and the metered voltage and outputs the voltage error to the training artificial neural network;
• and
• a separate estimating artificial neural network that determines a harmonic voltage component using the determined weights received from the training artificial neural network.