Method, system and equipment for detecting internal defects of high-performance epoxy insulating part and medium

Abstract

The invention belongs to the technical field of high-voltage insulation and fault diagnosis and discloses a high-performance epoxy insulator internal defect detection method, system and device and a medium. The high-performance epoxy insulator internal defect detection method comprises steps of carrying out preprocessing of a partial discharge signal of an epoxy insulator collected by an oscillatory wave test device; converting the time-distributed partial discharge signal into a cycle-by-cycle phase distribution mode, and counting the distribution of the discharge characteristic quantity of each cycle; performing feature extraction on the discharge feature quantity of each period by using a convolutional neural network to obtain abstract feature expression of each period so as to obtain an abstract feature sequence corresponding to the period; and processing the abstract feature sequence corresponding to the period by using a recurrent neural network, and then carrying out classification prediction. According to the method, effective information in periodic change is fully excavated and utilized, identification of the defect type of the epoxy insulating part under the oscillatory wave voltage is realized, and the defect type of the epoxy insulating part can be effectively identified with relatively high accuracy.

Description

technical field [0001] The invention belongs to the technical field of high-voltage insulation and fault diagnosis, and in particular relates to a method, system, equipment and medium for detecting internal defects of high-performance epoxy insulation parts. Background technique [0002] At present, the insulating part is the weak link in the high-voltage switchgear, and its performance will directly determine the insulation performance and operation reliability of the switchgear. For high-voltage switchgear, the improvement of its voltage level mainly depends on the performance of high-performance epoxy insulating parts, and its performance is mainly determined by whether there are tiny bubbles and crack defects inside it. Insulating materials in power equipment are subjected to electric fields, thermal fields, mechanical stress, etc. during operation, and microscopic defects such as air gaps or cracks are prone to occur inside. However, the detection accuracy of the existi...

AI Technical Summary

Problems solved by technology

[0004] Through the above analysis, the existing problems and defects of the prior art are: (1) AC withstand voltage detection: In the detection, there are often problems that the detection instrument does not change significantly but there are abnormal noises inside, and repeated detection is required to finally find out the cause and eliminate the abnormality. Noise, the insulating tape may be damaged during the withstand voltage test

(2) Insulation resistance detection: the workload of the line insulation test is relatively large

(3) DC withstand voltage detection: The devices for measuring on-site DC withstand voltage performance mainly include microammeters, high-resistors, resistor dividers, electrostatic high-voltage voltmeters, etc. Exposure to the air, due to the existence of wire ion flow, there will be a certain measurement error

In summary, the existing detection methods for the insulation state of power equipment have low detection accuracy, and the detection results are easily interfered by other defects

Images