scholarly journals Laser Cutting Defect Recognition Using Conversion of Processing Light Information into Spectrogram Images – Spectroscopic Measurements in Multiple Work Surface Conditions and Extraction of Spectral Data Features Based on Processing Principle –

2021 ◽  
Vol 15 (5) ◽  
pp. 728-739
Author(s):  
Mizuki Ishiguro ◽  
Rui Fukui ◽  
Shin’ichi Warisawa ◽  
Naoyasu Narita ◽  
Hironobu Miyoshi ◽  
...  
Keyword(s):  
Spectral Data ◽  
Laser Cutting ◽  
High Speed ◽  
Light Emission ◽  
Second Step ◽  
Support Vector ◽  
Analysis Software ◽  
Surface Conditions ◽  
Laser Head ◽  
Defect Recognition

At urban production sites, laser cutting is an essential technology for high-speed flexible sheet-metal processing. This study aims to detect defective cuts by sensing laser-cutting-induced light emission and elucidate meaningful features for processing-based detection. The proposed method comprises three steps. In the first step, the sensors installed in the laser head acquire the spectra of light generated during processing, and data analysis software converts the spectral data into spectrograms and stacked-graph images. In the second step, image processing software extracts the edges of both images and emphasizes the periodic features in normal laser cutting. In the final step, a one-class support vector machine recognizes defective cuts from the extracted features. Verification tests using multiple normal and abnormal cut data confirmed that the proposed method accurately detected defective cuts.

Durability Analysis of the Reduction Gear for High Speed Train Considering Driving Histories

2012 ◽  
Vol 586 ◽  
pp. 269-273
Author(s):  
Chul Su Kim ◽  
Gil Hyun Kang
Keyword(s):  
Fatigue Life ◽  
High Speed ◽  
Element Model ◽  
Rolling Stock ◽  
Reduction Gear ◽  
High Speed Train ◽  
Analysis Software ◽  
Tractive Effort ◽  
Durability Analysis ◽  
The Finite Element Model

To assure the safety of the power bogies for train, it is important to perform the durability analysis of reduction gear considering a variation of velocity and traction motor capability. In this study, two types of applied load histories were constructed from driving histories considering the tractive effort and the train running curves by using dynamic analysis software (MSC.ADAMS). Moreover, this study was performed by evaluating fatigue damage of the reduction gears for rolling stock using durability analysis software (MSC.FATIGUE). The finite element model for evaluating the carburizing effect on the gear surface was used for predicting the fatigue life of the gears. The results showed that the fatigue life of the reduction gear would decrease with an increasing numbers of stops at station.

Dynamic Analysis of DVG 850 High-Speed Machining Center

2012 ◽  
Vol 487 ◽  
pp. 203-207
Author(s):  
Gong Xue Zhang ◽  
Xiao Kai Shen
Keyword(s):  
High Speed ◽  
Simulation Analysis ◽  
Response Analysis ◽  
Improved Method ◽  
Analysis Software ◽  
Element Analysis ◽  
Harmonic Response ◽  
Machining Center ◽  
Calculation Results ◽  
Harmonic Response Analysis

Purpose, with the application of workbench finite element analysis software, get the analysis results of DVG 850 high-speed vertical machining center via the modal analysis and harmonic response analysis. Use the calculation results for reference, put forward the improved method, and prove the credibility of the simulation analysis by testing DVG 850 prototype.

CLASSIFICATION OF HIGH-DIMENSIONAL MICROARRAY DATA WITH A TWO-STEP PROCEDURE VIA A WILCOXON CRITERION AND MULTILAYER PERCEPTRON

2011 ◽  
Vol 10 (01) ◽  
pp. 1-14
Author(s):  
VLADIMIR NIKULIN ◽  
TIAN-HSIANG HUANG ◽  
GEOFFREY J. MCLACHLAN
Keyword(s):  
Data Mining ◽  
Feature Selection ◽  
High Dimensional ◽  
Second Step ◽  
Support Vector ◽  
Step Procedure ◽  
Leave One Out ◽  
Natural Combination ◽  
Feature Selection Techniques

The method presented in this paper is novel as a natural combination of two mutually dependent steps. Feature selection is a key element (first step) in our classification system, which was employed during the 2010 International RSCTC data mining (bioinformatics) Challenge. The second step may be implemented using any suitable classifier such as linear regression, support vector machine or neural networks. We conducted leave-one-out (LOO) experiments with several feature selection techniques and classifiers. Based on the LOO evaluations, we decided to use feature selection with the separation type Wilcoxon-based criterion for all final submissions. The method presented in this paper was tested successfully during the RSCTC data mining Challenge, where we achieved the top score in the Basic track.

Based on the CO2 Gas Shielded Welding Molten Pool Image Edge Detection Algorithm

2013 ◽  
Vol 437 ◽  
pp. 840-844 ◽  
Author(s):  
Xiao Gang Liu ◽  
Bing Zhao
Keyword(s):  
Edge Detection ◽  
Molten Pool ◽  
High Speed ◽  
Vision System ◽  
Detection Algorithm ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Low Pass ◽  
Defect Recognition ◽  
Pool Image

This paper use the passive vision system through high-speed camera collects molten pool images; and then according to the frequency domain characteristics of the weld pool image Butterworth low-pass filter; gradient method for image enhancement obtained after pretreatment. Research Roberts, Sobel, Prewitt, Log, Zerocross, and Canny 6 both traditional differential operator edge detection processing results. Through comparison and analysis of choosing threshold for [0.1, 0. Canny operator can get the ideal molten pool edge character, for subsequent welding molten pool defect recognition provides favorable conditions.

Strength of deposited high-speed steel in the process of gas laser cutting

2009 ◽  
Vol 51 (7-8) ◽  
pp. 352-355 ◽  
Author(s):  
L. E. Afanas’eva ◽  
I. A. Barabonova ◽  
N. S. Zubkov ◽  
M. S. Razumov
Keyword(s):  
Laser Cutting ◽  
High Speed ◽  
High Speed Steel ◽  
Gas Laser ◽  
Gas Laser Cutting

High-Speed Capturing of Stress Distribution of Workpiece under Ultrasonically Assisted Cutting Condition

2014 ◽  
Vol 1017 ◽  
pp. 747-752
Author(s):  
Hiromi Isobe ◽  
Keisuke Hara
Keyword(s):  
Stress Distribution ◽  
Cutting Force ◽  
High Speed ◽  
Cutting Tool ◽  
Light Emission ◽  
Cutting Speed ◽  
Cutting Condition ◽  
Photoelastic Method ◽  
Intermittent Cutting ◽  
Ultrasonic Vibration Cutting

This paper reports the stress distribution inside the workpiece under ultrasonic vibration cutting (UVC) condition. Many researchers have reported the improvement of tool wear, burr generation and surface integrity by reduction of time-averaged cutting force under UVC condition. However general dynamometers have an insufficient frequency band to observe the processing phenomena caused by UVC. In this paper, stress distribution inside the workpiece during UVC was observed by combining the flash light emission synchronized with ultrasonically vibrating cutting tool and the photoelastic method. Instantaneous stress distribution during UVC condition was observed. Because UVC induced an intermittent cutting condition, the stress distribution changed periodically and disappeared when the tool leaved from the workpiece. It was found that instantaneous maximum cutting force during UVC condition was smaller than quasi-static cutting force during conventional cutting when the cutting speed was less than 500 mm/min.

Headnote Prediction Using Machine Learning

2021 ◽  
Vol 18 (5) ◽  
Author(s):  
Sarmad Mahar ◽  
Sahar Zafar ◽  
Kamran Nishat
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Active Learning ◽  
Text Classification ◽  
Extraction Methods ◽  
Text Summarization ◽  
Training Data ◽  
Second Step ◽  
Support Vector ◽  
Classification Algorithms

Headnotes are the precise explanation and summary of legal points in an issued judgment. Law journals hire experienced lawyers to write these headnotes. These headnotes help the reader quickly determine the issue discussed in the case. Headnotes comprise two parts. The first part comprises the topic discussed in the judgment, and the second part contains a summary of that judgment. In this thesis, we design, develop and evaluate headnote prediction using machine learning, without involving human involvement. We divided this task into a two steps process. In the first step, we predict law points used in the judgment by using text classification algorithms. The second step generates a summary of the judgment using text summarization techniques. To achieve this task, we created a Databank by extracting data from different law sources in Pakistan. We labelled training data generated based on Pakistan law websites. We tested different feature extraction methods on judiciary data to improve our system. Using these feature extraction methods, we developed a dictionary of terminology for ease of reference and utility. Our approach achieves 65% accuracy by using Linear Support Vector Classification with tri-gram and without stemmer. Using active learning our system can continuously improve the accuracy with the increased labelled examples provided by the users of the system.

Sign in / Sign up

Export Citation Format

Share Document