Seam Detection Research Articles

On-Line Seam Detection in Rolling Processes Using Snake Projection and Discrete Wavelet Transform

This paper describes the development of an on-line quality inspection algorithm for detecting the surface defect “seam” generated in rolling processes. A feature-preserving “snake-projection” method is proposed for dimension reduction by converting the suspicious seam-containing images to one-dimensional sequences. Discrete wavelet transform is then performed on the sequences for feature extraction. Finally, a T2 control chart is established based on the extracted features to distinguish real seams from false positives. The snake-projection method has two parameters that impact the effectiveness of the algorithm. Thus, selection of the parameters is discussed. Implementation of the proposed algorithm shows that it satisfies the speed and accuracy requirements for on-line seam detection.

A vision-based algorithm for seam detection in a PAW process for large-diameter stainless steel pipes

Manual monitoring and seam tracking through welding images in real-time, by naked eye or industrial TV are experience-dependant, subjective, labor-intensive, and sometimes biased. So it is necessary to realize computer-aided seam tracking. We have developed a plasma arc welding (PAW) seam-tracking system, which senses the molten and the seam in a frame using a vision sensor, and then detects the seam deviation to adjust the work piece motion adaptively to the seam position sensed by the vision sensor with our collaborator. In this paper, we propose a novel molten pool area image-processing algorithm based on machine vision. The algorithm processes each image at a speed of 20 frames/s in real-time to extract three feature variables to get the seam deviation. It is proved experimentally that the algorithm is very fast and effective. Issues related to the algorithm are also discussed.

A study of a dual-electromagnetic sensor system for weld seam tracking of I-butt joints

Seam tracking systems for the arc welding process use various kinds of sensor including the arc sensor, vision sensor and laser displacement sensor. Among the various sensors available, the electromagnetic sensor is one of the most useful methods, especially in sheet metal butt-joint arc welding, primarily because it is hardly affected by the intense arc light and fumes generated during the welding process, or by the surface conditions of the weldment such as paint marks and scratches. In this study, a dual-electromagnetic sensor, which utilizes the induced current variation in the sensing coil due to the eddy current variation in the metal near the sensor, was developed for the arc welding of sheet metal I-butt joints. The dual-electromagnetic sensor thus detects the offset displacement of the weld line from the centre of the sensor head, even when there is no gap in the joint. A set of design variables for the sensor was examined to determine the maximum sensing capability through repeated experiments. Seam tracking was performed by correcting the position of the sensor to the amount of offset displacement determined during each sampling period. From the experimental results, the developed sensor system showed an excellent capability for weld seam detection and tracking when the sensor-to-workpiece distance was less than 5mm.

Electrical and gamma-ray logging in gondwana and tertiary coal fields of india

Electrical and gamma-ray logging have been very useful for identification and accurate determination of depth and thickness of coal seams in Gondwana and Tertiary coal fields of India. The characteristic resistance/resistivity peaks of coal seams in a particular area have been correlated, thus providing a picture of the subsurface structure. Physico-chemical properties of layers or sections of coal seams are responsive to electrical logs. Gammaray logs are found to be very useful for correlation and have sometimes been the only logs used in cased and dry boreholes for detection of coal seams. Under favourable conditions a single-point resistance log reveals a detailed picture of the formations and picks up thin coal seams as well as thin shale bands within the coal seam. But in some cases it fails to differentiate between coal and sandstone beds in spite of high contrast in true resistivities. Multi-electrode long-normal and lateral logs are found to be more useful in differentiating such formations because of higher penetration in this system. Long-normal and lateral curves can also be used to determine true resistivity of the formation. But long normal logs cannot pick up thin coal bands and/or thin shale partings within the coal seam because of the “adjacent bed effect”. Gamma-ray logging can be done in both cased and uncased boreholes or even in a dry borehole but its resolution for shaly coal or thin coal is not sufficient. Combined study has been found to yield the best results.