Partial discharge monitoring system and partial discharge monitoring method

1 . A partial discharge monitoring method comprising:

a signal measurement step of measuring signals of a high-voltage power device and obtaining pulse waveforms of the signals;

a signal separation step of extracting feature dots from the pulse waveforms and generating two-dimensional feature dot data using the feature dots;

a signal clustering step of clustering feature dot points corresponding to the feature dots on the two-dimensional feature dot data according to density to classify the feature dot points as feature dot data clusters, and obtaining phase resolved partial discharge (PRPD) data for the feature dot data clusters; and

a partial discharge determination step diagnosing the signals by recognizing patterns of the PRPD data and determining whether a partial discharge of the high-voltage power device has occurred on a basis of a diagnosis result,

wherein, in the signal clustering step, the feature dot points are clustered on a basis of density corresponding to a number of feature dot points present within a preset radius with respect to a specific feature dot point on the two-dimensional feature dot data obtained in the signal separation step.

2 . The partial discharge monitoring method of claim 1 , wherein the feature dots include shape parameters of pulses and bandwidths of the pulses into which the pulse waveforms are converted in a frequency domain.

3 . The partial discharge monitoring method of claim 1 , wherein, in the partial discharge determination step, a diagnosed signal is diagnosed as a normal signal when the diagnosed signal is a corona discharge signal or a noise signal, and the diagnosed signal is diagnosed as a partial discharge signal when the diagnosed signal is an internal discharge signal or a surface discharge signal to determine that the partial discharge has occurred due to a defect in the high-voltage power device.

4 . A partial discharge monitoring system comprising:

a signal detection unit provided with a sensor to detect signals of a power device;

a local unit configured to transmit the signals detected by the signal detection unit through a communication network; and

a main unit including:

a signal separation unit configured to extract feature dots from pulse waveforms of the signals transmitted through the local unit, and generate a two-dimensional feature dot using the extracted feature dots,;

a signal clustering unit configured to cluster feature dot points on two-dimensional feature dot data generated by the signal separation unit according to density to classify the feature dot points as feature dot data clusters, and generate phase resolved partial discharge (PRPD) data for the feature dot data clusters; and

a partial discharge determination unit configured to recognize patterns of the PRPD data generated by the signal clustering unit to diagnose the signals to determine whether a partial discharge of the power device has occurred based on a diagnosis,

wherein the signal clustering unit clusters feature dot points on the two-dimensional feature dot data obtained from the signal separation unit on a basis of density corresponding to a number of feature dot points present within a preset radius with respect to a specific feature dot point.

5 . The partial discharge monitoring system of claim 4 , wherein the feature dots include shape parameters of pulses and bandwidths of the pulses into which the pulse waveforms are converted in a frequency domain.

6 . The partial discharge monitoring system of claim 4 , wherein the partial discharge determination unit compares the PRPD data patterns and pulse waveforms of the signal clustering unit to learning data stored in a machine learning algorithm to diagnose the signals as one of a corona discharge signal, a noise signal, an internal discharge signal, and a surface discharge signal.