A Five-axis Contour Error Pre-compensation Method Based on Neural Network Prediction

Zhiqiang Liu; Jiangang Li; Yiming Fei; Yukang Lian

doi:10.23919/CCC55666.2022.9901811

A Five-axis Contour Error Pre-compensation Method Based on Neural Network Prediction

Zhiqiang Liu
, Jiangang Li^*
, Yiming Fei
, Yukang Lian

^*Corresponding author for this work

Harbin Institute of Technology Shenzhen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

In this article, a pre-compensation method is proposed for contour error control. This method predict the contour error indirectly using an imporoved neural network named Long and short-term Time-series network(LSTNet). By analyzing the characteristics of machine tool operation, the tracking error is divided into linear tracking error and nonlinear tracking error. The single-axis tracking error model is established using the neural network. First, the trajectory contour error is estimated according to the predicted trajectory and the reference trajectory. Then, the reference trajectory is compensated based on the predicted contour error. Finally, the experiment is implemented on a five-axis machine tool with BC revolving stage, and the results show that the proposed error compensation performs well.

Original language	English
Title of host publication	Proceedings of the 41st Chinese Control Conference, CCC 2022
Editors	Zhijun Li, Jian Sun
Publisher	IEEE Computer Society
Pages	2682-2687
Number of pages	6
ISBN (Electronic)	9789887581536
DOIs	https://doi.org/10.23919/CCC55666.2022.9901811
State	Published - 2022
Externally published	Yes
Event	41st Chinese Control Conference, CCC 2022 - Hefei, China Duration: 25 Jul 2022 → 27 Jul 2022

Publication series

Name	Chinese Control Conference, CCC
Volume	2022-July
ISSN (Print)	1934-1768
ISSN (Electronic)	2161-2927

Conference

Conference	41st Chinese Control Conference, CCC 2022
Country/Territory	China
City	Hefei
Period	25/07/22 → 27/07/22

Keywords

CNC systems
Contour error control
Neural network control

Access to Document

10.23919/CCC55666.2022.9901811

Cite this

@inproceedings{0b96d16e9fb345d6981eda92866d36f9,

title = "A Five-axis Contour Error Pre-compensation Method Based on Neural Network Prediction",

abstract = "In this article, a pre-compensation method is proposed for contour error control. This method predict the contour error indirectly using an imporoved neural network named Long and short-term Time-series network(LSTNet). By analyzing the characteristics of machine tool operation, the tracking error is divided into linear tracking error and nonlinear tracking error. The single-axis tracking error model is established using the neural network. First, the trajectory contour error is estimated according to the predicted trajectory and the reference trajectory. Then, the reference trajectory is compensated based on the predicted contour error. Finally, the experiment is implemented on a five-axis machine tool with BC revolving stage, and the results show that the proposed error compensation performs well.",

keywords = "CNC systems, Contour error control, Neural network control",

author = "Zhiqiang Liu and Jiangang Li and Yiming Fei and Yukang Lian",

note = "Publisher Copyright: {\textcopyright} 2022 Technical Committee on Control Theory, Chinese Association of Automation.; 41st Chinese Control Conference, CCC 2022 ; Conference date: 25-07-2022 Through 27-07-2022",

year = "2022",

doi = "10.23919/CCC55666.2022.9901811",

language = "英语",

series = "Chinese Control Conference, CCC",

publisher = "IEEE Computer Society",

pages = "2682--2687",

editor = "Zhijun Li and Jian Sun",

booktitle = "Proceedings of the 41st Chinese Control Conference, CCC 2022",

address = "美国",

}

Liu, Z, Li, J, Fei, Y & Lian, Y 2022, A Five-axis Contour Error Pre-compensation Method Based on Neural Network Prediction. in Z Li & J Sun (eds), Proceedings of the 41st Chinese Control Conference, CCC 2022. Chinese Control Conference, CCC, vol. 2022-July, IEEE Computer Society, pp. 2682-2687, 41st Chinese Control Conference, CCC 2022, Hefei, China, 25/07/22. https://doi.org/10.23919/CCC55666.2022.9901811

A Five-axis Contour Error Pre-compensation Method Based on Neural Network Prediction. / Liu, Zhiqiang; Li, Jiangang; Fei, Yiming et al.
Proceedings of the 41st Chinese Control Conference, CCC 2022. ed. / Zhijun Li; Jian Sun. IEEE Computer Society, 2022. p. 2682-2687 (Chinese Control Conference, CCC; Vol. 2022-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Five-axis Contour Error Pre-compensation Method Based on Neural Network Prediction

AU - Liu, Zhiqiang

AU - Li, Jiangang

AU - Fei, Yiming

AU - Lian, Yukang

PY - 2022

Y1 - 2022

N2 - In this article, a pre-compensation method is proposed for contour error control. This method predict the contour error indirectly using an imporoved neural network named Long and short-term Time-series network(LSTNet). By analyzing the characteristics of machine tool operation, the tracking error is divided into linear tracking error and nonlinear tracking error. The single-axis tracking error model is established using the neural network. First, the trajectory contour error is estimated according to the predicted trajectory and the reference trajectory. Then, the reference trajectory is compensated based on the predicted contour error. Finally, the experiment is implemented on a five-axis machine tool with BC revolving stage, and the results show that the proposed error compensation performs well.

AB - In this article, a pre-compensation method is proposed for contour error control. This method predict the contour error indirectly using an imporoved neural network named Long and short-term Time-series network(LSTNet). By analyzing the characteristics of machine tool operation, the tracking error is divided into linear tracking error and nonlinear tracking error. The single-axis tracking error model is established using the neural network. First, the trajectory contour error is estimated according to the predicted trajectory and the reference trajectory. Then, the reference trajectory is compensated based on the predicted contour error. Finally, the experiment is implemented on a five-axis machine tool with BC revolving stage, and the results show that the proposed error compensation performs well.

KW - CNC systems

KW - Contour error control

KW - Neural network control

UR - https://www.scopus.com/pages/publications/85140460374

U2 - 10.23919/CCC55666.2022.9901811

DO - 10.23919/CCC55666.2022.9901811

M3 - 会议稿件

AN - SCOPUS:85140460374

T3 - Chinese Control Conference, CCC

SP - 2682

EP - 2687

BT - Proceedings of the 41st Chinese Control Conference, CCC 2022

A2 - Li, Zhijun

A2 - Sun, Jian

PB - IEEE Computer Society

T2 - 41st Chinese Control Conference, CCC 2022

Y2 - 25 July 2022 through 27 July 2022

ER -

A Five-axis Contour Error Pre-compensation Method Based on Neural Network Prediction

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this