A Fault Diagnosis Method of High Voltage Circuit Breaker Based on Unsupervised Learning Model

Abstract

The invention discloses a high-voltage circuit breaker fault diagnosis method based on an unsupervised learning model, which includes: obtaining the coil current waveform during the opening and closing process of the high-voltage circuit breaker and obtaining the state parameters of the high-voltage circuit breaker according to the waveform; The vibration signal is sampled, and its time node t is selected; the high-voltage circuit breaker fault is classified and numbered as the output of the fault model identification system, and the coil current, vibration signal and time node are input to the fault model identification system; the noise reduction self- As a typical unsupervised learning model, the decoding algorithm is used to train the model. Using the SVM structure, the loss function obtained by the noise reduction self-encoding algorithm is used to obtain the regression expression of the circuit breaker fault; according to the regression expression of the circuit breaker fault, the occurrence The corresponding relationship between the coil current data and the fault type at the time of fault, and then the fault type is determined by the fault data to be determined. The training optimization process of the present invention can avoid local optimal solutions.

Description

Technical field [0001] The invention relates to the field of high-voltage circuit breaker fault diagnosis, in particular to a high-voltage circuit breaker fault diagnosis method based on an unsupervised learning model. Background technique [0002] The safety of power transmission and transformation equipment is the basis for the safe operation of the power grid. Comprehensive and accurate evaluation, diagnosis and prediction of the equipment status are the prerequisites for the maintenance of the power transmission and transformation equipment and life cycle management, and it is to improve the reliability of power supply and the power grid. An important way to operate the intelligent level is also an important basis for intelligent dispatching operation, which can provide strong technical support for the safe, reliable and economic operation of the power grid. [0003] Foreign countries have carried out early research on the monitoring technology of high-voltage equipment status ...

AI Technical Summary

Problems solved by technology

First of all, the circuit breaker has a very complex mechanical structure, and the environmental factors on site have non-negligible noise interference, so that the vibration signal monitored by the sensor has a large natural error.

In fact, a certain number of vibration processes will be generated to varying degrees during the opening and closing operations of the circuit breaker, and the complex changes in the physical parameters of the vibration signal and other parameters in the actual operation, including the dispersion, reflection and refraction of the vibration signal, make the monitoring work difficult. become more difficult, sometimes even more difficult to monitor when the vibration signal is negligible

Images