Circuit breaker fault type judgment method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of circuit breaker fault type judgment, in particular to a circuit breaker fault type judgment method and device, electronic equipment and a storage medium. The detection method comprises the following steps: obtaining a sound time-frequency diagram and a vibration time-frequency diagram of sound signals and vibration signals of a circuit breaker; respectively carrying out feature extraction on the sound time-frequency diagram and the vibration time-frequency diagram through a double-channel CNN model to obtain a corresponding sound feature diagramand a vibration feature diagram, and carrying out feature fusion on the sound feature diagram and the vibration feature diagram to obtain a fusion feature diagram; and using the classifier to determine the fault type according to the fusion feature map. According to the embodiment of the invention, the dual-channel CNN model is adopted to extract feature maps of the sound time-frequency diagram and the vibration time-frequency diagram respectively; the extracted sound feature map and the extracted vibration feature map are fused to obtain richer image features, and finally, the fault type is obtained through the classifier according to the fused fused feature map, so that the identification accuracy of circuit breaker fault type judgment is improved.

Description

technical field [0001] The invention relates to the technical field of circuit breaker fault type judgment, in particular to a circuit breaker fault type judgment method, device, electronic equipment and storage medium. Background technique [0002] The power system is developing in the direction of large-capacity, ultra-high voltage and cross-regional power transmission, which puts forward higher requirements for the safe operation of electrical equipment. With the full implementation of the national smart grid construction and the ubiquitous Internet of Things, online monitoring and diagnosis of electrical equipment in operation are widely carried out to achieve timely and accurate status assessment of equipment and early detection of inherent defects and hidden dangers. A job becomes more and more important. However, the measurement link of circuit breaker on-line monitoring signal acquisition is easily affected by the strong magnetic field, strong electric field, equipm...

AI Technical Summary

Problems solved by technology

[0005] The above studies have achieved certain results in the judgment of mechanical fault types, but lack of signal purification processing, the feature extraction process is complex, requires manual intervention, and the accuracy of fault identification is not high due to the limitation of sample data volume

Images