Tool Wear State Identification Method with Variable Cutting Parameters Based on Multi-Source Unsupervised Domain Adaptation

Accurately identifying tool wear states with variable cutting parameters can improve machining quality and efficiency. However, existing wear state recognition methods based on unsupervised domain adaptation mostly employ the knowledge transfer learning strategy in a single source domain. They canno...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhigang Cai, Wangyang Li, Jianxin Song, Hongyu Jin, Hongya Fu
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/6/1742
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850280263258472448
author Zhigang Cai
Wangyang Li
Jianxin Song
Hongyu Jin
Hongya Fu
author_facet Zhigang Cai
Wangyang Li
Jianxin Song
Hongyu Jin
Hongya Fu
author_sort Zhigang Cai
collection DOAJ
description Accurately identifying tool wear states with variable cutting parameters can improve machining quality and efficiency. However, existing wear state recognition methods based on unsupervised domain adaptation mostly employ the knowledge transfer learning strategy in a single source domain. They cannot fully utilize the sensor data distribution information of multiple cutting parameters, hindering recognition performance improvement. Thus, this paper proposes a wear-state recognition method for variable cutting parameters based on multi-source unsupervised domain adaptation. First, non-stationary Transformer encoders extract non-stationary common features; then, sliced Wasserstein distance-based domain-specific feature distribution alignment and classifier output alignment scale down the domain shift and make multi-domain distribution synchronous alignment less complex. Finally, the milling experiments with variable cutting parameters are conducted to validate the recognition performance of the proposed method.
format Article
id doaj-art-c092f0ae37094cbc879b639a36f25bb2
institution OA Journals
issn 1424-8220
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-c092f0ae37094cbc879b639a36f25bb22025-08-20T01:48:49ZengMDPI AGSensors1424-82202025-03-01256174210.3390/s25061742Tool Wear State Identification Method with Variable Cutting Parameters Based on Multi-Source Unsupervised Domain AdaptationZhigang Cai0Wangyang Li1Jianxin Song2Hongyu Jin3Hongya Fu4School of Mechatronic Engineering, Harbin Institute of Technology, Harbin 150001, ChinaInspur Genersoft Co., Ltd., Jinan 250101, ChinaSchool of Mechatronic Engineering, Harbin Institute of Technology, Harbin 150001, ChinaSchool of Mechatronic Engineering, Harbin Institute of Technology, Harbin 150001, ChinaSchool of Mechatronic Engineering, Harbin Institute of Technology, Harbin 150001, ChinaAccurately identifying tool wear states with variable cutting parameters can improve machining quality and efficiency. However, existing wear state recognition methods based on unsupervised domain adaptation mostly employ the knowledge transfer learning strategy in a single source domain. They cannot fully utilize the sensor data distribution information of multiple cutting parameters, hindering recognition performance improvement. Thus, this paper proposes a wear-state recognition method for variable cutting parameters based on multi-source unsupervised domain adaptation. First, non-stationary Transformer encoders extract non-stationary common features; then, sliced Wasserstein distance-based domain-specific feature distribution alignment and classifier output alignment scale down the domain shift and make multi-domain distribution synchronous alignment less complex. Finally, the milling experiments with variable cutting parameters are conducted to validate the recognition performance of the proposed method.https://www.mdpi.com/1424-8220/25/6/1742tool wear state identificationtransfer learningmulti-source unsupervised domain adaptionvarying cutting parameters
spellingShingle Zhigang Cai
Wangyang Li
Jianxin Song
Hongyu Jin
Hongya Fu
Tool Wear State Identification Method with Variable Cutting Parameters Based on Multi-Source Unsupervised Domain Adaptation
Sensors
tool wear state identification
transfer learning
multi-source unsupervised domain adaption
varying cutting parameters
title Tool Wear State Identification Method with Variable Cutting Parameters Based on Multi-Source Unsupervised Domain Adaptation
title_full Tool Wear State Identification Method with Variable Cutting Parameters Based on Multi-Source Unsupervised Domain Adaptation
title_fullStr Tool Wear State Identification Method with Variable Cutting Parameters Based on Multi-Source Unsupervised Domain Adaptation
title_full_unstemmed Tool Wear State Identification Method with Variable Cutting Parameters Based on Multi-Source Unsupervised Domain Adaptation
title_short Tool Wear State Identification Method with Variable Cutting Parameters Based on Multi-Source Unsupervised Domain Adaptation
title_sort tool wear state identification method with variable cutting parameters based on multi source unsupervised domain adaptation
topic tool wear state identification
transfer learning
multi-source unsupervised domain adaption
varying cutting parameters
url https://www.mdpi.com/1424-8220/25/6/1742
work_keys_str_mv AT zhigangcai toolwearstateidentificationmethodwithvariablecuttingparametersbasedonmultisourceunsuperviseddomainadaptation
AT wangyangli toolwearstateidentificationmethodwithvariablecuttingparametersbasedonmultisourceunsuperviseddomainadaptation
AT jianxinsong toolwearstateidentificationmethodwithvariablecuttingparametersbasedonmultisourceunsuperviseddomainadaptation
AT hongyujin toolwearstateidentificationmethodwithvariablecuttingparametersbasedonmultisourceunsuperviseddomainadaptation
AT hongyafu toolwearstateidentificationmethodwithvariablecuttingparametersbasedonmultisourceunsuperviseddomainadaptation