Lipei Jiang

Study on a Pipe Welding Robot based on Laser Vision Sensing

A type of pipe welding robot system was studied. It recognizes and tracks the groove in two dimensions using one laser visual sensor. When the first layer seam is real-time tracked and welded, the groove information is memorized by robot, and the work of teaching robot is completed at the same time. Experimental results verify that the welding seam tracking can meet the needs of the automatization of pipe welding process.

Welding deviation detection algorithm based on extremum of molten pool image contour

The welding deviation detection is the basis of robotic tracking welding, but the on-line real-time measurement of welding deviation is still not well solved by the existing methods. There is plenty of information in the gas metal arc welding(GMAW) molten pool images that is very important for the control of welding seam tracking. The physical meaning for the curvature extremum of molten pool contour is revealed by researching the molten pool images, that is, the deviation information points of welding wire center and the molten tip center are the maxima and the local maxima of the contour curvature, and the horizontal welding deviation is the position difference of these two extremum points. A new method of weld deviation detection is presented, including the process of preprocessing molten pool images, extracting and segmenting the contours, obtaining the contour extremum points, and calculating the welding deviation, etc. Extracting the contours is the premise, segmenting the contour lines is the foundation, and obtaining the contour extremum points is the key. The contour images can be extracted with the method of discrete dyadic wavelet transform, which is divided into two sub contours including welding wire and molten tip separately. The curvature value of each point of the two sub contour lines is calculated based on the approximate curvature formula of multi-points for plane curve, and the two points of the curvature extremum are the characteristics needed for the welding deviation calculation. The results of the tests and analyses show that the maximum error of the obtained on-line welding deviation is 2 pixels(0.16 mm), and the algorithm is stable enough to meet the requirements of the pipeline in real-time control at a speed of less than 500 mm/min. The method can be applied to the on-line automatic welding deviation detection.

Surface Reconstruction from Sparse & Arbitrarily Oriented Contours in Freehand 3D Ultrasound

3D reconstruction for freehand 3D ultrasound is a challenging issue because the recorded B-scans are not only sparse, but also non-parallel (actually they may arbitrarily oriented in 3D space and may intersect each other). Conventional volume reconstruction methods can’t reconstruct sparse data efficiently while not introducing geometrical artifacts, and conventional surface reconstruction methods can’t reconstruct surfaces from contours that are arbitrarily oriented in 3D space. We developed a new surface reconstruction method for freehand 3D ultrasound based on variational implicit function which is presented by Greg Turk for shape transformation. In the new method, we first constructed on- & off-surface constraints from the segmented contours of all recorded B-scans, then used a variational interpolation technique to get a single implicit function in 3D. Finally, the implicit function was evaluated to extract the zero-valued surface as final reconstruction result. Two experiment was conducted to assess our variational surface reconstruction method, and the experiment results have shown that the new method is capable of reconstructing surface smoothly from sparse contours which can be arbitrarily oriented in 3D space.

Weld pool image processing algorithm for seam tracking of welding robot

A weld pool image processing algorithm based passive-light-vision has been studied in this paper. Firstly, we have designed a kind of method to directly capture the welding pool images of Gas Metal Arc Welding (GMAW) by a CCD camera with a narrowband filter. Next, using the median filter and wavelet transform eliminates noise and keeps the details of the image effectively. Then, we have proposed to adopt the threshold image segmentation for detecting the welding pool in the image. The segmentation between the connected components and the noises to include the welding pool with the spots and the block, have been realized by the method to mark the connected pixels. Finally, through the operations of pixel-by-column scanning and pixel-by-line scanning, the groove centerline and the welding torch centerline can be found out correctly and the deviations of the seam are also obtained. The experiment and analysis have illustrated that wavelet transform can effectively filter out the image noise, maintain the details of the image and prevent the boundaries blurred, the T of 180 is the most suitable threshold and the deviation in different conditions can be calculated. This algorithm can be used in the seam tracking of welding robot.

Intelligent wheeled mobile robot for spherical tank welding

At present, spherical tank manufacture is still staying at the level of manual welding or semi-automation. In order to improve quality of weld seam and guarantee safe operating of spherical tank, automatic welding equipment is needed urgently. A intelligent wheeled mobile robot equipped with CCD based visual sensor has been developed to acquire better weld quality in this research. Special mechanical structure has been proposed based a wheeled mobile robot body to realize reliably and flexibly absorbing and moving on the surface of spherical tank. A 3-DOF welding manipulator has been fixed on the robot to carry out welding tasks. A CCD sensor has been used to detect weld seam for the trajectory planing of both the mobile robot and the welding torch, control strategy for nonholonomic system with redundant DOF has been put forward to realize the accurate tracing of weld torch, an intelligent controller has been designed. In this paper, mechanical structure of robot, principle of CCD sensor, tracing model for robot and welding torch, and intelligent controller have been presented in details respectively. Experiments show that this robot can fulfill all-position welding tasks freely on the surface of tank with high weld torch tracing accuracy(up to +/- 0.5mm).

Variational Surface Reconstruction from Sparse and Nonparallel Contours for Freehand 3D Ultrasound

3D reconstruction for freehand 3D ultrasound is a challenging issue because the recorded B-scans are not only sparse, but also non-parallel. Both conventional volume and surface reconstruction methods can’t reconstruct sparse data efficiently while they are arbitrarily oriented in 3D space. We developed a new surface reconstruction method for freehand 3D ultrasound based on variational implicit function. In the new method, we first constructed on- & off-surface constraints from the segmented contours of all recorded B-scans, then used a variational interpolation technique to get a single implicit function in 3D. Finally, the implicit function was evaluated to extract the zero-valued surface as reconstruction result. One phantom experiment was conducted to assess our variational surface reconstruction method, and the experiment results have shown that the new method is capable of reconstructing surface smoothly from sparse contours which can be arbitrarily oriented in 3D space.

A Needle-Holding Robot for Ultrasound Guided Percutaneous Hepatic Microwave Ablation and Initial Experiments

A needle-holding robot for percutaneous hepatic microwave ablation is developed. The overall architecture of the robot is introduced first with the explanation of the mechanism of 3D motion tracking. Two experiments were conducted, one to quantify the force required for motion tracking, the other to assess the performance of motion tracking. The result of force-measuring experiment shows that the force required for rotation and radial translation motion tracking are less than 15 grams, which indicates the high sensitivity of the holding robot. The result of in-vivo animal trial performed on a swine shows that the holding robot is accurate enough in tracking the 3D motion of the ablation needle, which allows for stable and precise holding of the needle compared to that of freehand holding.

Weld Seam Edge Extraction Algorithm Based on Beamlet Transform

We present a novel algorithm based on Beamlet Transform for extracting seam edges from noisy welding images. Taking into account of some special characteristics of welding image processing, we introduce an orientation-thresholding step as well as a two-scan method to the standard beamlet-based line detection algorithm. Experiments are conducted to extract edge features from noisy welding images at different scales and to test the anti-noising performance of our algorithm. The result of experiments show that our algorithm is capable of directly extracting weld seam edges from highly noisy welding images without any pre-processing or post-processing steps, thus is characterized by its high efficiency and its prominent anti-noising performance. The orientation threshold can not only reduce the calculation load, expedite its running speed, but also it can help to improve the anti-noising performance of the algorithm. The two-scan method is particularly helpful when coping with low SNR welding images.

Linear CCD based novel visual sensor for intelligent spherical tank welding robot

In order to fulfill autonomous climbing and automatic weld seam tracking, a novel visual sensor has been developed for intelligent spherical tank welding robot. Composed of a high-resolution linear CCD, an optical system (including light source, filter, lenses and so on), and an all hardware photoelectrical signal processing circuit, the designed visual sensor could avoid the interference of the arc light during welding and provide the seam track signal precisely in real time. In this paper, the construction and working principle of the linear CCD based visual sensor have been illustrated, then principle of weld seam track detecting has been introduced thoroughly. Equipped with the visual sensor, the spherical tank welding robot could move along the weld seam autonomously, could align the welding torch with weld seam automatically. Therefore, the requirements of multi-layer, multi-pass welding process for spherical tank manufacturing have been met.