Current transformer and bus current detecting method based on neural network

Abstract

The invention discloses a current transformer and a bus current detecting method based on a neural network. The current transformer comprises an incident optical path, a sensing optical path and a reflection optical path. A fast tunable optical attenuator with ultra-low power consumption is used in the current transformer. The current transformer has the advantages of being low in power consumption, high stability and good in insulation performance. The bus current detecting method based on the neural network comprises the steps that the temperature of an environment where the current transformer located is obtained by using an optical fiber bragg grating, an edge filter and optical fiber shaking eliminating processing, output signals of the current transformer are obtained through the optical fiber shaking eliminating processing, neural network training is carried out by using given bus currents, current transformer temperature and output of the current transformer, and the bus current detecting method is achieved. The bus current detecting method is high in measurement precision and low in temperature drift.

Description

technical field [0001] The invention belongs to the field of power system monitoring and protection, and relates to an ultra-low power consumption current transformer and a neural network-based high-precision, low-temperature drift bus current detection method. Background technique [0002] In the operation of power production, transmission and power equipment, current and voltage need to be measured, and the sensor device that obtains current and voltage information is a transformer, which converts a large current or high voltage on the high voltage side into a small current on the low voltage side or low voltage. Accurate, reliable and high-performance transformers are one of the important guarantees to ensure the safe, reliable and efficient operation of the power grid. [0003] Traditional transformers are mainly electromagnetic transformers, but their inherent shortcomings such as magnetic saturation, ferromagnetic resonance, small dynamic range, narrow frequency band ...

AI Technical Summary

Problems solved by technology

People use the Pockels Effect (PockelsEffect) and Faraday Effect (FaradyEffect) to develop a series of pure optical current and voltage transformers. The method is direct, the device is simple, and the precision is high. Sensitive to light fluctuations, poor measurement stability

In 2001, Huazhong University of Science and Technology proposed an OCT solution using Rogowski coils, integrators and voltage-frequency converters, using the traditional CT energy supply solution, but due to the large power consumption of the voltage-frequency converter, the overall power consumption of OCT Not significantly reduced

However, due to the influence of crystal nonlinearity and passive integration circuit, its actual accuracy is not ideal

Images