Multi-channel Parallel BiLSTM-Based Tool Residual Life Prediction Under Complex Working Conditions

Hanyang Wang; Ming Luo; Fengshou Gu

doi:10.1007/978-3-032-01363-7_70

Multi-channel Parallel BiLSTM-Based Tool Residual Life Prediction Under Complex Working Conditions

Hanyang Wang^*, Ming Luo, Fengshou Gu

^*Corresponding author for this work

University of Bristol Business School

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

Abstract

The prediction of remaining tool life under complex working conditions has become the key to guarantee the machining quality and machining efficiency. In this paper, MCWDCNN is constructed as a milling cutter wear state identification model, and the vibration data of plane milling is used for model validation. For plane milling data, the envelope spectral information of the two signal processes in one cycle of forward milling and reverse milling is used as the input data of the model dual-channel, and the tool life prediction model under complex working conditions is constructed through the BiLSTM and attention mechanism, and the vibration signal sample data set is constructed by using the tool health factor and the RMS as the labels, respectively, and is inputted into the tool life prediction model, and the result has a higher The results have a high degree of fit, which verifies the effectiveness and generalizability of the tool life prediction model.

Original language	English
Title of host publication	Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences, UNIfied 2025 - Volume 2
Editors	Xiong Shu, Yun Zhu, Hongxiang Zou, Bingyan Chen
Publisher	Springer Science and Business Media B.V.
Pages	869-880
Number of pages	12
Volume	2
ISBN (Electronic)	9783032013637
ISBN (Print)	9783032013620
DOIs	https://doi.org/10.1007/978-3-032-01363-7_70
Publication status	E-pub ahead of print - 2 Oct 2026
Event	UNIfied Conference of International Conference on Damage Assessment of Structures, DAMAS 2025, International Conference on Maintenance Engineering, IncoME 2025 and The Efficiency and Performance Engineering, TEPEN 2025 - Zhangjiajie, China Duration: 16 May 2025 → 19 May 2025 https://unified2025.uauuu.com/

Publication series

Name	Mechanisms and Machine Science
Volume	189
ISSN (Print)	2211-0984
ISSN (Electronic)	2211-0992

Conference

Conference	UNIfied Conference of International Conference on Damage Assessment of Structures, DAMAS 2025, International Conference on Maintenance Engineering, IncoME 2025 and The Efficiency and Performance Engineering, TEPEN 2025
Country/Territory	China
City	Zhangjiajie
Period	16/05/25 → 19/05/25
Internet address	https://unified2025.uauuu.com/

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Keywords

BiLSTM
Convolution neural network
Remaining useful life
Tool

Access to Document

10.1007/978-3-032-01363-7_70

Handle.net

Persistent link

Cite this

Wang, H., Luo, M., & Gu, F. (2026). Multi-channel Parallel BiLSTM-Based Tool Residual Life Prediction Under Complex Working Conditions. In X. Shu, Y. Zhu, H. Zou, & B. Chen (Eds.), Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences, UNIfied 2025 - Volume 2 (Vol. 2, pp. 869-880). (Mechanisms and Machine Science; Vol. 189). Springer Science and Business Media B.V.. Advance online publication. https://doi.org/10.1007/978-3-032-01363-7_70

Wang, Hanyang ; Luo, Ming ; Gu, Fengshou. / Multi-channel Parallel BiLSTM-Based Tool Residual Life Prediction Under Complex Working Conditions. Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences, UNIfied 2025 - Volume 2. editor / Xiong Shu ; Yun Zhu ; Hongxiang Zou ; Bingyan Chen. Vol. 2 Springer Science and Business Media B.V., 2026. pp. 869-880 (Mechanisms and Machine Science).

@inproceedings{d8694549584740108ca7f10c15f25625,

title = "Multi-channel Parallel BiLSTM-Based Tool Residual Life Prediction Under Complex Working Conditions",

abstract = "The prediction of remaining tool life under complex working conditions has become the key to guarantee the machining quality and machining efficiency. In this paper, MCWDCNN is constructed as a milling cutter wear state identification model, and the vibration data of plane milling is used for model validation. For plane milling data, the envelope spectral information of the two signal processes in one cycle of forward milling and reverse milling is used as the input data of the model dual-channel, and the tool life prediction model under complex working conditions is constructed through the BiLSTM and attention mechanism, and the vibration signal sample data set is constructed by using the tool health factor and the RMS as the labels, respectively, and is inputted into the tool life prediction model, and the result has a higher The results have a high degree of fit, which verifies the effectiveness and generalizability of the tool life prediction model.",

keywords = "BiLSTM, Convolution neural network, Remaining useful life, Tool",

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

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.; UNIfied Conference of International Conference on Damage Assessment of Structures, DAMAS 2025, International Conference on Maintenance Engineering, IncoME 2025 and The Efficiency and Performance Engineering, TEPEN 2025 ; Conference date: 16-05-2025 Through 19-05-2025",

year = "2026",

month = oct,

day = "2",

doi = "10.1007/978-3-032-01363-7\_70",

language = "English",

isbn = "9783032013620",

volume = "2",

series = "Mechanisms and Machine Science",

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

pages = "869--880",

editor = "Xiong Shu and Yun Zhu and Hongxiang Zou and Bingyan Chen",

booktitle = "Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences, UNIfied 2025 - Volume 2",

address = "Netherlands",

url = "https://unified2025.uauuu.com/",

}

Wang, H, Luo, M & Gu, F 2026, Multi-channel Parallel BiLSTM-Based Tool Residual Life Prediction Under Complex Working Conditions. in X Shu, Y Zhu, H Zou & B Chen (eds), Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences, UNIfied 2025 - Volume 2. vol. 2, Mechanisms and Machine Science, vol. 189, Springer Science and Business Media B.V., pp. 869-880, UNIfied Conference of International Conference on Damage Assessment of Structures, DAMAS 2025, International Conference on Maintenance Engineering, IncoME 2025 and The Efficiency and Performance Engineering, TEPEN 2025, Zhangjiajie, China, 16/05/25. https://doi.org/10.1007/978-3-032-01363-7_70

Multi-channel Parallel BiLSTM-Based Tool Residual Life Prediction Under Complex Working Conditions. / Wang, Hanyang; Luo, Ming; Gu, Fengshou.
Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences, UNIfied 2025 - Volume 2. ed. / Xiong Shu; Yun Zhu; Hongxiang Zou; Bingyan Chen. Vol. 2 Springer Science and Business Media B.V., 2026. p. 869-880 (Mechanisms and Machine Science; Vol. 189).

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

TY - GEN

T1 - Multi-channel Parallel BiLSTM-Based Tool Residual Life Prediction Under Complex Working Conditions

AU - Wang, Hanyang

AU - Luo, Ming

AU - Gu, Fengshou

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

PY - 2026/10/2

Y1 - 2026/10/2

N2 - The prediction of remaining tool life under complex working conditions has become the key to guarantee the machining quality and machining efficiency. In this paper, MCWDCNN is constructed as a milling cutter wear state identification model, and the vibration data of plane milling is used for model validation. For plane milling data, the envelope spectral information of the two signal processes in one cycle of forward milling and reverse milling is used as the input data of the model dual-channel, and the tool life prediction model under complex working conditions is constructed through the BiLSTM and attention mechanism, and the vibration signal sample data set is constructed by using the tool health factor and the RMS as the labels, respectively, and is inputted into the tool life prediction model, and the result has a higher The results have a high degree of fit, which verifies the effectiveness and generalizability of the tool life prediction model.

AB - The prediction of remaining tool life under complex working conditions has become the key to guarantee the machining quality and machining efficiency. In this paper, MCWDCNN is constructed as a milling cutter wear state identification model, and the vibration data of plane milling is used for model validation. For plane milling data, the envelope spectral information of the two signal processes in one cycle of forward milling and reverse milling is used as the input data of the model dual-channel, and the tool life prediction model under complex working conditions is constructed through the BiLSTM and attention mechanism, and the vibration signal sample data set is constructed by using the tool health factor and the RMS as the labels, respectively, and is inputted into the tool life prediction model, and the result has a higher The results have a high degree of fit, which verifies the effectiveness and generalizability of the tool life prediction model.

KW - BiLSTM

KW - Convolution neural network

KW - Remaining useful life

KW - Tool

UR - https://www.scopus.com/pages/publications/105027128245

U2 - 10.1007/978-3-032-01363-7_70

DO - 10.1007/978-3-032-01363-7_70

M3 - Conference Contribution (Conference Proceeding)

AN - SCOPUS:105027128245

SN - 9783032013620

VL - 2

T3 - Mechanisms and Machine Science

SP - 869

EP - 880

BT - Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences, UNIfied 2025 - Volume 2

A2 - Shu, Xiong

A2 - Zhu, Yun

A2 - Zou, Hongxiang

A2 - Chen, Bingyan

PB - Springer Science and Business Media B.V.

T2 - UNIfied Conference of International Conference on Damage Assessment of Structures, DAMAS 2025, International Conference on Maintenance Engineering, IncoME 2025 and The Efficiency and Performance Engineering, TEPEN 2025

Y2 - 16 May 2025 through 19 May 2025

ER -

Wang H, Luo M, Gu F. Multi-channel Parallel BiLSTM-Based Tool Residual Life Prediction Under Complex Working Conditions. In Shu X, Zhu Y, Zou H, Chen B, editors, Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences, UNIfied 2025 - Volume 2. Vol. 2. Springer Science and Business Media B.V. 2026. p. 869-880. (Mechanisms and Machine Science). Epub 2026 Oct 2. doi: 10.1007/978-3-032-01363-7_70

Multi-channel Parallel BiLSTM-Based Tool Residual Life Prediction Under Complex Working Conditions

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this