基于KF-GPR的熔池关键特征建模方法

Hang Dong; Ming Cong; Yuming Zhang; Heping Chen

doi:10.12073/j.hjxb.2018390296

基于KF-GPR的熔池关键特征建模方法

Hang Dong
, Ming Cong
, Yuming Zhang
, Heping Chen

Producción científica: Article › revisión exhaustiva

1 Cita (Scopus)

Resumen

To help an automatic welding machine on reasoning dynamic welding process, a Kalman Filter Gaussian Process Regression (KF-GPR) model was proposed, and its theoretical basis was annualized. A prediction model was established later. Compared to conventional statistic method, the KF-GRP method can better estimate the distributed form and parameters for a dynamic welding process, which had higher robustness and fault tolerance. TIG welding experiment of the 304 stainless steel was carried out to verify the method. Totally 8 423 pairs of experiment data were collected and used for the model. The modeling results showed the proposed KF-GPR can suppress noises and provide fast and accurate model, which is essential for future online control experiment.

Título traducido de la contribución	Characteristic performance modeling method for weld pool based on KF-GPR
Idioma original	Chinese (Simplified)
Páginas (desde-hasta)	49-52
Número de páginas	4
Publicación	Hanjie Xuebao/Transactions of the China Welding Institution
Volumen	39
N.º	12
DOI	https://doi.org/10.12073/j.hjxb.2018390296
Estado	Published - dic 25 2018

Nota bibliográfica

Publisher Copyright:
© 2018, Editorial Board of Transactions of the China Welding Institution, Magazine Agency Welding. All right reserved.

ASJC Scopus subject areas

Mechanics of Materials
Mechanical Engineering

Acceder al documento

10.12073/j.hjxb.2018390296

Otros archivos y enlaces

Citar esto

@article{987b80ed246d455a954a34f1024bd7e7,

title = "基于KF-GPR的熔池关键特征建模方法",

abstract = "To help an automatic welding machine on reasoning dynamic welding process, a Kalman Filter Gaussian Process Regression (KF-GPR) model was proposed, and its theoretical basis was annualized. A prediction model was established later. Compared to conventional statistic method, the KF-GRP method can better estimate the distributed form and parameters for a dynamic welding process, which had higher robustness and fault tolerance. TIG welding experiment of the 304 stainless steel was carried out to verify the method. Totally 8 423 pairs of experiment data were collected and used for the model. The modeling results showed the proposed KF-GPR can suppress noises and provide fast and accurate model, which is essential for future online control experiment.",

keywords = "Critical characteristic performance, Dynamic welding process, GPR, Kalman filter",

author = "Hang Dong and Ming Cong and Yuming Zhang and Heping Chen",

year = "2018",

month = dec,

day = "25",

doi = "10.12073/j.hjxb.2018390296",

language = "Chinese (Simplified)",

volume = "39",

pages = "49--52",

number = "12",

}

TY - JOUR

T1 - 基于KF-GPR的熔池关键特征建模方法

AU - Dong, Hang

AU - Cong, Ming

AU - Zhang, Yuming

AU - Chen, Heping

PY - 2018/12/25

Y1 - 2018/12/25

N2 - To help an automatic welding machine on reasoning dynamic welding process, a Kalman Filter Gaussian Process Regression (KF-GPR) model was proposed, and its theoretical basis was annualized. A prediction model was established later. Compared to conventional statistic method, the KF-GRP method can better estimate the distributed form and parameters for a dynamic welding process, which had higher robustness and fault tolerance. TIG welding experiment of the 304 stainless steel was carried out to verify the method. Totally 8 423 pairs of experiment data were collected and used for the model. The modeling results showed the proposed KF-GPR can suppress noises and provide fast and accurate model, which is essential for future online control experiment.

AB - To help an automatic welding machine on reasoning dynamic welding process, a Kalman Filter Gaussian Process Regression (KF-GPR) model was proposed, and its theoretical basis was annualized. A prediction model was established later. Compared to conventional statistic method, the KF-GRP method can better estimate the distributed form and parameters for a dynamic welding process, which had higher robustness and fault tolerance. TIG welding experiment of the 304 stainless steel was carried out to verify the method. Totally 8 423 pairs of experiment data were collected and used for the model. The modeling results showed the proposed KF-GPR can suppress noises and provide fast and accurate model, which is essential for future online control experiment.

KW - Critical characteristic performance

KW - Dynamic welding process

KW - GPR

KW - Kalman filter

UR - https://www.scopus.com/pages/publications/85061989365

UR - https://www.scopus.com/pages/publications/85061989365#tab=citedBy

U2 - 10.12073/j.hjxb.2018390296

DO - 10.12073/j.hjxb.2018390296

M3 - Article

AN - SCOPUS:85061989365

SN - 0253-360X

VL - 39

SP - 49

EP - 52

JO - Hanjie Xuebao/Transactions of the China Welding Institution

JF - Hanjie Xuebao/Transactions of the China Welding Institution

IS - 12

ER -

基于KF-GPR的熔池关键特征建模方法

Resumen

Nota bibliográfica

ASJC Scopus subject areas

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto