Contactless Measurement of Substation Busbars Voltages and Waveforms Reconstruction Using Electric Field Sensors and Artificial Neural Network

Abstract

This paper presents a method for contactless measurement of instantaneous voltage and waveform reconstruction for use in a medium voltage (MV) indoor substation. Voltage waveforms are reconstructed by artificial neural network (ANN) using the signals originating from electric field sensors located under MV bus. The method is validated by the experiment in a typical indoor MV substation. Depending on the selection of ANN architecture and data used for training the root mean squared error of waveforms, reconstruction as low as 0.3% to 2.1% can be achieved in a steady state. The practical advice on the application of the proposed measurement method in a production environment is also given. Index Terms-Artificial neural networks (ANN), contactless voltage measurement, electric field (EF) sensors, waveform reconstruction.

Optimisation electric field inverse solving algorithm for non‐destructive detection of voltage on transmission lines

“…According to the superposition principle, both simulating line charges and matching points are partitioned equally on the transmission lines. The simulating charge matrix Q can be written as (see (8)) , where n is the number of conductors, m is the number of simulating line charges and matching points of each conductor, Q i, k is the ith simulating line charge density of the kth conductor, φ j, k is the voltage of the jth matching point of the kth conductor, P i, j, k is the potential coefficient of the ith matching point and the jth simulating line charges of the kth conductor. the expression of P i, j, k written by numerical calculation is…”

“…The electric field numerical integral method measures the conductor potential indirectly by taking measurement of the electric field intensity around the conductor integral, which is premised on the linear relation between the conductor potential and the surrounding electric field. The method is implemented by installing the designed sensor on the transmission line [7], designing simple electric field sensor, putting them under the transmission line in order [8,9], and optimising the integral interval of the integral algorithm [10]. At present, the method displays many disadvantages.…”

Non‐intrusive sensing method of the phasor of system voltage for partial discharge diagnostics

“…Among these methods, EF sensors are deployed under the overhead lines [15] or busbars, including insulators [16] or in the vicinity of a cable [16]. Borkowski et al [17] have proposed a method for contactless measurement of instantaneous voltage and waveform reconstruction for use in a medium voltage indoor substation based on artificial neural network algorithm. Shimada et al [18] designed a non‐contact and real‐time transducer mounted on overhead conductors to measure system voltages.…”

Contactless voltage sensor for overhead transmission lines

“…There were other technologies to attain the optimal coupling matrix instead of physical measurement in other applications. For example, Borkowski et al in [20] presented an accurate voltage sensor used for the busbars in substations. In fact, this method needs a standard value obtained from a reference voltage divider, for a complicated calibration using artificial neural network.…”

“…Table 1 summarises a comparison between the existing methods and the proposed method. Even though these studies in [14,15,[17][18][19][20] show high sensing accuracy, It will be even harder to implement them into the field measurement because of the calibration procedure. Compared with the method in [23], our method using only three sensors, which is more suitable for the actual field measurement.…”