Power equipment infrared thermogram identification method combining deep learning with traditional algorithm
A technology of electric power equipment and infrared heat map, which is applied in character and pattern recognition, calculation, computer parts and other directions, can solve the problems of poor real-time performance, low recognition efficiency, high misjudgment rate, etc., to achieve wide practicability and reduce dependence precise, high-precision
Pending Publication Date: 2021-03-16
ZHEJIANG TIANBO CLOUD TECH OPTOELECTRONICS CO LTD
View PDF5 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In the existing power transmission and transformation lines, in order to ensure the normal operation of various power equipment in the power transmission and transformation lines, it is necessary to conduct regular inspections on the power equipment. The traditional manual inspection mode requires staff to manually check the equipment through the monitoring system. There are problems such as high labor cost, poor real-time performance, and high misjudgment rate when judging the state of the power equipment. The recognition rate of electric equipment is low
At the same time, the existing intelligent inspection scheme for power equipment based on deep learning uses target detection algorithms (such as Faster R-CNN, YOLO, SSD) to process infrared heat images. These algorithms must first locate the power equipment in the image, and then Then carry out the recognition operation, the recognition efficiency is low, and it cannot meet the existing needs; therefore, it is necessary to invent a new infrared heat map recognition method for power equipment to solve the current problems
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0023] A method for identifying infrared thermal images of power equipment based on deep learning combined with traditional algorithms, comprising the following steps:
[0024] 1) Obtain infrared heat map data sets of 50 types of electrical equipment, each category has 1000 pieces, extract the temperature information in the image, and store it as floating-point data;
[0025] 2), normalize the data set, set the image size to 256*256, so that the value is distributed between 0 and 1;
[0026] 3) Perform a histogram equalization operation on the image to improve the contrast;
[0027] 4) Use the Gaussian-Laplacian operator for filtering to enhance the details while ensuring that the noise in the original data is suppressed to a certain extent. After the sharpened image is obtained, it is superimposed on the original image;
[0028] 5) Randomly scramble the order of the data sets and randomly divide the training set, verification set, and test set at a ratio of 6:2:2, and send t...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a power equipment infrared thermogram identification method combining deep learning with a traditional algorithm. The method comprises the following steps: using Gaussian filtering to carry out smooth noise point operation on a data set; performing high-frequency information extraction operation on the data set by using a Laplace filter; using histogram transformation for assistance; and training the processed data set by using a Faster RCNN network, and performing parameter adjustment to finally obtain a model capable of effectively detecting the power equipment in theinfrared thermogram. Effective features of a data set are highlighted through a traditional algorithm, dependence between similar pixels is reduced, the features are more obvious, and the Faster RCNNnetwork can effectively train a model with higher accuracy.
Description
technical field [0001] The invention relates to a recognition method of an infrared heat map of electric equipment based on deep learning combined with traditional algorithms. Background technique [0002] Infrared image of power equipment is an infrared detection technology that detects the infrared radiation energy emitted by power equipment and converts it into a corresponding electrical signal, and obtains a thermal image of the surface of power equipment after electrical signal processing; Sampling, non-disintegration, accurate, fast, intuitive and other characteristics are widely used in the detection and diagnosis of power equipment, which is of great significance to improving the stability of the power system. [0003] In the existing power transmission and transformation lines, in order to ensure the normal operation of various power equipment in the power transmission and transformation lines, it is necessary to conduct regular inspections on the power equipment. T...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/04
CPCG06N3/045G06F18/251G06F18/214
Inventor 梁川朱怡良
Owner ZHEJIANG TIANBO CLOUD TECH OPTOELECTRONICS CO LTD