TY - GEN
T1 - Weld defect recognition method of pipeline based on improved least squares twin support vector machine
AU - Xianming, Lang
AU - Hao, Zheng
AU - Huadong, Song
AU - Jinhai, Liu
AU - Xiaoting, Guo
AU - Qiang, Meng
AU - Haitao, Yuan
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/6/22
Y1 - 2021/6/22
N2 - To improve the recognition accuracy of the weld and weld detect in the pipeline inspection, an identification method based on least squares twin support vector machine (LSTSVM) is proposed. The magnetic flux leakage (MFL) signal features are extracted according to the fluctuation and shape features, which are input into LSTSVM, LSTSVM to recognize weld, weld detect, detect and normal condition. Particle swarm optimization is used to optimize the penalty parameters and kernel parameters of LSTSVM to achieve high identification accuracy. The experimental results show that the recognition accuracy of the proposed method is 98.7%, which is higher than those of back propagation neural network, support vector machine and LSTSVM.
AB - To improve the recognition accuracy of the weld and weld detect in the pipeline inspection, an identification method based on least squares twin support vector machine (LSTSVM) is proposed. The magnetic flux leakage (MFL) signal features are extracted according to the fluctuation and shape features, which are input into LSTSVM, LSTSVM to recognize weld, weld detect, detect and normal condition. Particle swarm optimization is used to optimize the penalty parameters and kernel parameters of LSTSVM to achieve high identification accuracy. The experimental results show that the recognition accuracy of the proposed method is 98.7%, which is higher than those of back propagation neural network, support vector machine and LSTSVM.
KW - Identification method
KW - Least squares twin support vector machine
KW - Magnetic flux leakage
KW - Weld detect
UR - https://www.scopus.com/pages/publications/85113651521
U2 - 10.1109/MED51440.2021.9480203
DO - 10.1109/MED51440.2021.9480203
M3 - 会议稿件
AN - SCOPUS:85113651521
T3 - 2021 29th Mediterranean Conference on Control and Automation, MED 2021
SP - 500
EP - 505
BT - 2021 29th Mediterranean Conference on Control and Automation, MED 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 29th Mediterranean Conference on Control and Automation, MED 2021
Y2 - 22 June 2021 through 25 June 2021
ER -