Power equipment image data warehouse and power equipment defect detection method

Abstract

The invention relates to a power equipment image data warehouse and a power equipment defect detection method; detection images of a multi-dimensional data star model organization mode are stored in the data warehouse, and each detection image is associated with corresponding detected equipment operation information, time information, geographic information, environment monitoring information anddetection information; the defect detection method comprises the following steps: constructing a sample library based on historical data in the data warehouse; training a support vector machine for defect detection based on the sample library; acquiring image features of the to-be-detected power equipment, fusing the environment information features and the detection information features, and performing detection and classification through a trained support vector machine; and according to the detection result, positioning the equipment defect occurrence time and position through the index. Compared with the prior art, the method has the advantages of high defect detection efficiency and accuracy and the like.

Description

technical field [0001] The invention relates to the fields of distributed storage, database establishment and management, image recognition, and electric equipment defect detection, and in particular relates to a power equipment image data warehouse and a power equipment defect detection method. Background technique [0002] With the gradual improvement of the power grid structure, the number of power equipment is increasing year by year, and the maintenance workload is increasing day by day. Due to problems such as equipment quality and insufficient operation and maintenance, the number of equipment defects and failures also increase accordingly. The safe and stable operation of equipment plays a big role. However, traditional manual inspection consumes more time and energy. Therefore, it is necessary to combine image recognition to detect equipment defects. With the development of image detection of electric power equipment, the image data related to defect detection is i...

AI Technical Summary

Problems solved by technology

However, traditional manual inspection consumes more time and energy. Therefore, it is necessary to combine image recognition to detect equipment defects.

With the development of image detection of electric power equipment, the image data related to defect detection increases rapidly, the data volume is large, the data sources are diverse, the data value density is low, and the value is not fully utilized, resulting in data waste

It takes a lot of manpower and time to manage images in the form of folders, and it is difficult to add and expand, and it cannot fully interact with researchers who are not inspectors. The data openness is low, and it is difficult to carry out automatic discrimination research on power equipment status.

Images