35KV prefabricated cabin acceptance test method and system

By performing grayscale processing and feature extraction on the target detection images of the 35 kV prefabricated cabin, combined with the intelligent identification of the feature enhancement processing model and the welding defect detection model, the problem of difficulty in detecting small defects in existing methods is solved, and the accuracy and stability of the sealing detection of the 35 kV prefabricated cabin is improved.

CN119722572APending Publication Date: 2025-03-28GUANGDONG POWER GRID CO LTD
0 Cites 0 Cited by

Patent Information

Application Number
CN202411577376.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-06
Publication Date
2025-03-28

AI Technical Summary

Technical Problem

When performing sealing acceptance tests on the 35 kV prefabricated chamber, the existing methods are prone to miss tiny appearance defects, such as fine cracks in the surface coating and tiny pores inside the welded part, resulting in a reduction in sealing in subsequent use, affecting performance and stability.

Method used

A 35 kV prefabricated chamber acceptance and testing method is adopted, and the target detection image is acquired, converted into grayscale images and edge processing is performed. The feature enhancement processing model and welding defect detection model are further intelligently identified to accurately detect welding defects.

Benefits of technology

This method can accurately detect welding defects in the 35 kV prefabricated chamber, improve sealing, enhance the performance and stability of the equipment, and avoid the limitations of manual observation and tool measurement.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a 35-kilovolt prefabricated cabin acceptance test method and system. The method comprises the following steps: acquiring a target detection image of a target 35-kilovolt prefabricated cabin to be accepted and tested; converting the target detection image into a grayscale image, and performing edge processing on the grayscale image to obtain a feature map after edge processing; inputting the edge-processed feature graph into a feature enhancement processing model to obtain a feature-enhanced graph of the edge-processed feature graph output by the feature enhancement processing model; and inputting the feature-enhanced image into a welding defect detection model to obtain a welding defect detection result of the target 35-kilovolt prefabricated cabin output by the welding defect detection model. The welding defect detection model is obtained by training based on the sample feature image and the corresponding welding defect detection result label. According to the method, the welding defect detection result of the target 35-kilovolt prefabricated cabin can be accurately obtained, so that the sealing performance of the 35-kilovolt prefabricated cabin can be accurately detected, and the performance and the stability of the 35-kilovolt prefabricated cabin are improved.
Need to check novelty before this filing date? Find Prior Art