Classification of Plume Image and Analysis of Welding Stability during High Power Disc Laser Welding

2012 ◽  
Vol 201-202 ◽  
pp. 1139-1142 ◽  
Author(s):  
Qian Wen ◽  
Xiang Dong Gao
Keyword(s):  
Laser Welding ◽  
High Power ◽  
Nearest Neighbor ◽  
Welding Process ◽  
Welding Quality ◽  
K Nearest Neighbor ◽  
Dimension Vector ◽  
Absolute Value ◽  
Neighbor Classification

Plume images which captured during the high power disc laser welding contain lots of information that related to the welding quality and stability. The classification of plume images is an important foundation for online monitoring during welding process. Stainless steel 304 was taken as the experiment object for the high power disc laser welding experiments. A high-speed camera was used to capture the ultraviolet band and visible light band plume images in the laser welding process. Image processing techniques were applied to get the characteristic parameters such as the ratio of the absolute value of coordinate difference between the centriod of plume and the welding point, the number of spatter, the average gray level and entropy of a spatter image, and formed a four dimension vector. Then K-nearest neighbor classification method was used to separate the poor welding quality images out from good ones. Welding experimental results confirmed that using K- nearest neighbor classification method to classify the four dimension vector samples which formed by the ratio of absolute value of coordinate difference between the centriod of plume and welding point, number of spatters, average gray level and entropy could obtain a recognition rate that close to the actual welding results.

Analysis of Characteristic of Metal Vapor Plume during High-Power Disc Laser Welding

2012 ◽  
Vol 201-202 ◽  
pp. 1126-1129
Author(s):  
Qian Wen ◽  
Xiang Dong Gao
Keyword(s):  
Laser Welding ◽  
High Power ◽  
High Speed ◽  
Welding Process ◽  
Metal Vapor ◽  
Welding Quality ◽  
Absolute Value ◽  
Coordinate Difference ◽  
Vapor Plume ◽  
The Absolute

Metal vapor plume which induced during high power disc laser welding contains lots of information that related to the welding quality. Stainless steel 304 was taken as the experiment object for the high power disc laser welding experiment. A high-speed camera was used to capture the ultraviolet band and visible light band metal vapor plume images in the laser welding process. Image processing techniques such as median filtering, Wiener filtering, gray level threshold and image binarization were applied to get the images that only metal vapor plume was included. The ratio of the absolute value of coordinate difference between the centroid of plume and welding point was taken as the characteristic parameter. Welding experimental results and analysis of the changing of the ratio of the absolute value of coordinate difference between the centroid of plume and welding point confirmed that the welding quality could be monitored by the metal vapor plume during high power disc laser welding.

Segmentation of Molten Pool Infrared Images Using Morphology during High Power Disk Laser Welding

2012 ◽  
Vol 201-202 ◽  
pp. 91-94
Author(s):  
Yan Xi Zhang ◽  
Xiang Dong Gao
Keyword(s):  
Laser Welding ◽  
High Power ◽  
Molten Pool ◽  
Welding Process ◽  
Histogram Equalization ◽  
Welding Quality ◽  
Infrared Images ◽  
Traditional Methods ◽  
Disk Laser ◽  
Laser Welding Process

Configuration of a molten pool is related to the laser welding quality. Analyzing the configuration of a molten pool is important to monitor the laser welding process. This paper proposes a method of segmentation of a molten pool and its shadow during high power disk laser welding, consequently provides the groundwork for reconstruction of the molten pool and analysis of welding quality. Subsection linear stretching histogram equalization was applied to enhance the contrast of the original images firstly, and then edge detection was used to highlight the edges. After that we used the morphology filtering method to produce the segmentation mask, and then combined the mask with the original images to get the final segmentation results. Also, the proposed method was compared with other traditional methods. The experimental results showed that our method not only could give better segmentation results and process large quantities images automatically, but also overcame the less-segmentation problems of traditional methods.

scholarly journals A proposed method for handling an imbalance data in classification of blood type based on Myers-Briggs type indicator

2020 ◽  
Vol 8 (4) ◽  
pp. 276-283
Author(s):  
Ahmad Taufiq Akbar ◽  
Rochmat Husaini ◽  
Bagus Muhammad Akbar ◽  
Shoffan Saifullah
Keyword(s):  
Nearest Neighbor ◽  
Data Use ◽  
Blood Type ◽  
K Nearest Neighbor ◽  
Myers Briggs Type Indicator ◽  
Imbalance Data ◽  
Type Indicator ◽  
Testing Data ◽  
Neighbor Classification

Blood type still leads to an assumption about its relation to some personality aspects. This study observes preprocessing methods for improving the classification accuracy of MBTI data to determine blood type. The training and testing data use 250 data from the MBTI questionnaire answers given by 250 respondents. The classification uses the k-Nearest Neighbor (k-NN) algorithm. Without preprocessing, k-NN results in about 32 % accuracy, so it needs some preprocessing to handle data imbalance before the classification. The proposed preprocessing consists of two-stage, the first stage is the unsupervised resample, and the second is the supervised resample. For the validation, it uses ten cross-validations. The result of k-Nearest Neighbor classification after using these proposed preprocessing stages has finally increased the accuracy, F-score, and recall significantly.

Extraction of Characteristic Parameters of Keyhole during High Power Fiber Laser Welding

2012 ◽  
Vol 201-202 ◽  
pp. 352-355
Author(s):  
Yong Hua Liu ◽  
Xiang Dong Gao
Keyword(s):  
Laser Welding ◽  
Fiber Laser ◽  
High Power ◽  
Continuous Wave ◽  
Welding Process ◽  
Detection Methods ◽  
Deep Penetration ◽  
Welding Quality ◽  
Characteristic Parameters ◽  
Fiber Laser Welding

During deep penetration laser welding, a keyhole is formed in the molten pool. The characteristics of keyhole are related to the welding quality and stability. Analyzing the characteristic parameters of a keyhole during high power fiber laser welding is one of effective measures to control the welding quality and improve the welding stability. This paper studies a fiber laser butt-joint welding of Type 304 austenitic stainless steel plate with a high power 10 kW continuous wave fiber laser, and an infrared sensitive high-speed video camera was used to capture the dynamic images of the molten pools. A combination filtering system with a filter length of 960-990nm in front of the vision sensor was used to obtain the near infrared image and eliminate other light disturbances. The width, the area, the leftmost point, the rightmost point, the upmost point and the bottommost point of a keyhole were defined as the keyhole characteristic parameters. By using the image preprocessing method, such as median filtering, Wiener filtering, threshold segmentation and Canny edge detection methods, the characteristic parameters of a keyhole were obtained. By analyzing the change of the keyhole characteristic parameters during welding process, it was found that these parameters could reflect the quality and stability of laser welding effectively.

scholarly journals A k-nearest neighbor classification of hERG K+ channel blockers

2016 ◽  
Vol 30 (3) ◽  
pp. 229-236 ◽  
Author(s):  
Swapnil Chavan ◽  
Ahmed Abdelaziz ◽  
Jesper G. Wiklander ◽  
Ian A. Nicholls
Keyword(s):  
Nearest Neighbor ◽  
K Channel ◽  
Channel Blockers ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Classification ◽  
Neighbor Classification

scholarly journals Detection and Classification of Caterpillar using Image Processing with K-Nearest Neighbor Classification Technique

2021 ◽  
Vol 12 (5) ◽  
pp. 719-728
Author(s):  
Dr. Mukta Jagdish, Andres Medina Guzman, Gerber F. Incacari Sancho, Aura Guerrero-Luzuriaga
Keyword(s):  
Image Processing ◽  
Nearest Neighbor ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Classifier ◽  
Self Defense ◽  
Classification Technique ◽  
Buck Moth ◽  
Neighbor Classification ◽  
Neighbor Classifier

Caterpillars are the developmental stage of the flying insect called butterfly. The moths are the beautiful creature of earth which comes under the class of insects. They are recognized by their beautiful and colorful forewings body and legs. Caterpillars are the larval stage of the moth which are found in the leaf and stem of the plants when the moth laid eggs on the leaves after their mating. Caterpillar after fully developed from its eggs draw out a flimsy, soft cocoon made up of dark coarse silk on leaves and stem for their shelter. Caterpillar is also a beautiful creature that is found with different colors and strips with spines and urticating hair in their body for releasing venom for self-defense from external predators. The present study works on the detection and classification of the caterpillar using image processing with a k-NN classifier.This research help in characterizing the type of caterpillar image classification for particular three classes such as accuracy of Buck Moth Caterpillar, the accuracy of Saddleback Caterpillar, and the accuracy of Io moth Caterpillar. The following stages have been considered are preprocessing, segmentation, feature extraction, and classification methods using K- Nearest Neighbor classifier. The present investigation results that SYMLET5 analysis works well in the classification of the caterpillar with an accuracy of 96% using K- Nearest Neighbor classifier compare with other measures during investigation and analysis.

Sign in / Sign up

Export Citation Format

Share Document