Multi-domain Features Fusion Adaptive Neural Network Tool Wear Recognition Model

Hanyang Wang; Ming Luo; Fengshou Gu

doi:10.1007/978-3-031-26193-0_66

Multi-domain Features Fusion Adaptive Neural Network Tool Wear Recognition Model

Hanyang Wang
, Ming Luo^*
, Fengshou Gu

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

1 Citation (Scopus)

Abstract

The condition of cutting tools is affecting the product quality, production cost and profit. Monitoring the condition correctly and accurately is very import in machining industry. In this paper, a tool wear recognition model based on adaptive neural networks with multi-domain feature fusion is presented. First, the vibration signals obtained from the sensors mounted on the working area is processed to generate the time-domain and frequency-domain features, which form a multi-dimension space. Then the core features are identified according to the distance criteria. Finally, LSTM neural network is used to determine the tool wear condition during the machining process by processing the core features. The model is verified by the data collected from industry practical experiments. The results shows that our model can successfully increase the precision of tool wear classification and has certain generalization ability under different working conditions compared with the single eigenvalue prediction method.

Original language	English
Title of host publication	Proceedings of TEPEN 2022 - Efficiency and Performance Engineering Network
Editors	Hao Zhang, Yongjian Ji, Tongtong Liu, Xiuquan Sun, Andrew David Ball
Publisher	Springer Science and Business Media B.V.
Pages	751-765
Number of pages	15
ISBN (Print)	9783031261923
DOIs	https://doi.org/10.1007/978-3-031-26193-0_66
Publication status	Published - 2023
Event	International Conference of The Efficiency and Performance Engineering Network, TEPEN 2022 - Baotou, China Duration: 18 Aug 2022 → 21 Aug 2022

Publication series

Name	Mechanisms and Machine Science
Volume	129 MMS
ISSN (Print)	2211-0984
ISSN (Electronic)	2211-0992

Conference

Conference	International Conference of The Efficiency and Performance Engineering Network, TEPEN 2022
Country/Territory	China
City	Baotou
Period	18/08/22 → 21/08/22

Bibliographical note

Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

ANN adaptive neural network
CNC
Multi-domain features
Tool wear status

Access to Document

10.1007/978-3-031-26193-0_66

Handle.net

Persistent link

Cite this

Wang, H., Luo, M., & Gu, F. (2023). Multi-domain Features Fusion Adaptive Neural Network Tool Wear Recognition Model. In H. Zhang, Y. Ji, T. Liu, X. Sun, & A. D. Ball (Eds.), Proceedings of TEPEN 2022 - Efficiency and Performance Engineering Network (pp. 751-765). (Mechanisms and Machine Science; Vol. 129 MMS). Springer Science and Business Media B.V.. https://doi.org/10.1007/978-3-031-26193-0_66

Wang, Hanyang ; Luo, Ming ; Gu, Fengshou. / Multi-domain Features Fusion Adaptive Neural Network Tool Wear Recognition Model. Proceedings of TEPEN 2022 - Efficiency and Performance Engineering Network. editor / Hao Zhang ; Yongjian Ji ; Tongtong Liu ; Xiuquan Sun ; Andrew David Ball. Springer Science and Business Media B.V., 2023. pp. 751-765 (Mechanisms and Machine Science).

@inproceedings{7420b320cbc34c7d8b6c3674f786a8cd,

title = "Multi-domain Features Fusion Adaptive Neural Network Tool Wear Recognition Model",

abstract = "The condition of cutting tools is affecting the product quality, production cost and profit. Monitoring the condition correctly and accurately is very import in machining industry. In this paper, a tool wear recognition model based on adaptive neural networks with multi-domain feature fusion is presented. First, the vibration signals obtained from the sensors mounted on the working area is processed to generate the time-domain and frequency-domain features, which form a multi-dimension space. Then the core features are identified according to the distance criteria. Finally, LSTM neural network is used to determine the tool wear condition during the machining process by processing the core features. The model is verified by the data collected from industry practical experiments. The results shows that our model can successfully increase the precision of tool wear classification and has certain generalization ability under different working conditions compared with the single eigenvalue prediction method.",

keywords = "ANN adaptive neural network, CNC, Multi-domain features, Tool wear status",

author = "Hanyang Wang and Ming Luo and Fengshou Gu",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; International Conference of The Efficiency and Performance Engineering Network, TEPEN 2022 ; Conference date: 18-08-2022 Through 21-08-2022",

year = "2023",

doi = "10.1007/978-3-031-26193-0\_66",

language = "English",

isbn = "9783031261923",

series = "Mechanisms and Machine Science",

publisher = "Springer Science and Business Media B.V.",

pages = "751--765",

editor = "Hao Zhang and Yongjian Ji and Tongtong Liu and Xiuquan Sun and Ball, \{Andrew David\}",

booktitle = "Proceedings of TEPEN 2022 - Efficiency and Performance Engineering Network",

address = "Netherlands",

}

Wang, H, Luo, M & Gu, F 2023, Multi-domain Features Fusion Adaptive Neural Network Tool Wear Recognition Model. in H Zhang, Y Ji, T Liu, X Sun & AD Ball (eds), Proceedings of TEPEN 2022 - Efficiency and Performance Engineering Network. Mechanisms and Machine Science, vol. 129 MMS, Springer Science and Business Media B.V., pp. 751-765, International Conference of The Efficiency and Performance Engineering Network, TEPEN 2022, Baotou, China, 18/08/22. https://doi.org/10.1007/978-3-031-26193-0_66

Multi-domain Features Fusion Adaptive Neural Network Tool Wear Recognition Model. / Wang, Hanyang; Luo, Ming; Gu, Fengshou.
Proceedings of TEPEN 2022 - Efficiency and Performance Engineering Network. ed. / Hao Zhang; Yongjian Ji; Tongtong Liu; Xiuquan Sun; Andrew David Ball. Springer Science and Business Media B.V., 2023. p. 751-765 (Mechanisms and Machine Science; Vol. 129 MMS).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Multi-domain Features Fusion Adaptive Neural Network Tool Wear Recognition Model

AU - Wang, Hanyang

AU - Luo, Ming

AU - Gu, Fengshou

PY - 2023

Y1 - 2023

N2 - The condition of cutting tools is affecting the product quality, production cost and profit. Monitoring the condition correctly and accurately is very import in machining industry. In this paper, a tool wear recognition model based on adaptive neural networks with multi-domain feature fusion is presented. First, the vibration signals obtained from the sensors mounted on the working area is processed to generate the time-domain and frequency-domain features, which form a multi-dimension space. Then the core features are identified according to the distance criteria. Finally, LSTM neural network is used to determine the tool wear condition during the machining process by processing the core features. The model is verified by the data collected from industry practical experiments. The results shows that our model can successfully increase the precision of tool wear classification and has certain generalization ability under different working conditions compared with the single eigenvalue prediction method.

AB - The condition of cutting tools is affecting the product quality, production cost and profit. Monitoring the condition correctly and accurately is very import in machining industry. In this paper, a tool wear recognition model based on adaptive neural networks with multi-domain feature fusion is presented. First, the vibration signals obtained from the sensors mounted on the working area is processed to generate the time-domain and frequency-domain features, which form a multi-dimension space. Then the core features are identified according to the distance criteria. Finally, LSTM neural network is used to determine the tool wear condition during the machining process by processing the core features. The model is verified by the data collected from industry practical experiments. The results shows that our model can successfully increase the precision of tool wear classification and has certain generalization ability under different working conditions compared with the single eigenvalue prediction method.

KW - ANN adaptive neural network

KW - CNC

KW - Multi-domain features

KW - Tool wear status

UR - https://www.scopus.com/pages/publications/85151149187

U2 - 10.1007/978-3-031-26193-0_66

DO - 10.1007/978-3-031-26193-0_66

M3 - Conference Contribution (Conference Proceeding)

AN - SCOPUS:85151149187

SN - 9783031261923

T3 - Mechanisms and Machine Science

SP - 751

EP - 765

BT - Proceedings of TEPEN 2022 - Efficiency and Performance Engineering Network

A2 - Zhang, Hao

A2 - Ji, Yongjian

A2 - Liu, Tongtong

A2 - Sun, Xiuquan

A2 - Ball, Andrew David

PB - Springer Science and Business Media B.V.

T2 - International Conference of The Efficiency and Performance Engineering Network, TEPEN 2022

Y2 - 18 August 2022 through 21 August 2022

ER -

Multi-domain Features Fusion Adaptive Neural Network Tool Wear Recognition Model

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this