Detection method for identifying water drops in seamless steel tube outer surface three-dimensional detection
A seamless steel pipe, three-dimensional inspection technology, applied in neural learning methods, measurement devices, image data processing and other directions, can solve the problems of real defect confusion, detection interference, false alarms of detection equipment, etc., to achieve suitable promotion and use, reduce detection errors Effect
A seamless steel pipe, three-dimensional inspection technology, applied in neural learning methods, measurement devices, image data processing and other directions, can solve the problems of real defect confusion, detection interference, false alarms of detection equipment, etc., to achieve suitable promotion and use, reduce detection errors Effect
CN112198170APending Publication Date: 2021-01-08ACADEMY OF PUBLIC SECURITY TECH HEFEI
Image
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0034] see Figure 1-3 , the present invention provides a technical solution:
[0035] A detection method for identifying water droplets in three-dimensional detection of the outer surface of a seamless steel pipe, comprising the following steps:
[0036] Step 1: Data preprocessing: According to the pipe body profile data obtained by the three-dimensional sensor, generate a two-dimensional grayscale image of the surface of the pipe body, and preprocess the grayscale image to obtain all areas to be detected;
[0037] Step 2: Model training: construct a deep learning network suitable for detecting water droplets on the steel pipe surface offline, and train the model offline with the images of the area to be detected collected in step 1;
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 relates to the technical field of three-dimensional detection of the outer surface of a steel pipe, in particular to a detection method for identifying water drops in three-dimensional detection of the outer surface of a seamless steel pipe. The detection method comprises data preprocessing, model training and online detection. According to the method, the seamless steel pipe is detected through three steps of data preprocessing, model training and online detection, in actual production, the three-dimensional laser sensor splices contour lines of a pipe body and converts the contour lines into a to-be-detected steel pipe surface depth map, and a water drop detection model is used for detecting the depth map; according to the method, morphological operation and out-of-region search are carried out on the depth image to obtain the to-be-detected region suspected to be water drops, and then a convolutional neural network is used for identifying the to-be-detected region, sothat the water drops on the surface of the steel pipe can be accurately identified, the steel pipe three-dimensional detection false alarm is greatly reduced, the detection time is short, and the method is suitable for popularization and application.
Description
technical field [0001] The invention relates to the technical field of three-dimensional detection of the outer surface of a steel pipe, in particular to a detection method for identifying water droplets in the nondestructive detection of the outer surface of a seamless steel pipe. Background technique [0002] Hot-rolled seamless steel pipes need to be sprayed and cooled during the production process, especially when passing through ultrasonic testing equipment, water needs to be sprayed as a couplant, resulting in sometimes water droplets on the surface of the pipe body. When the three-dimensional sensor is used to collect the profile data of the pipe body, the water droplets appear as depressions, protrusions, and both depressions and protrusions on the depth map. The shape is mainly oval in the center with horizontal stripes on both sides. Different steel pipes have changeable shapes on the surface, which is easy to be confused with real defects, which seriously interfer...
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
08 Jan 2021
Publication
CN112198170A
- IPC
- G01N21/952; G01B11/24; G06T7/00; G06T7/12; G06T7/181; G06T7/187; G06N3/04; G06N3/08
- CPC
- G01N21/952; G01B11/24; G06T7/0004; G06T7/12; G06T7/181; G06T7/187; G06N3/08; G06T2207/10028
- Inventors
- 窦曼莉; 刘小楠