Finite Element Modeling-Assisted Deep Subdomain Adaptation Method for Tool Condition Monitoring DOI Open Access

Jing Cong,

Xin He, Guirong Xu

et al.

Processes, Journal Year: 2025, Volume and Issue: 13(2), P. 545 - 545

Published: Feb. 15, 2025

To reduce the experimental costs associated with tool condition monitoring (TCM) under new cutting conditions, a finite element modeling (FEM)-assisted deep subdomain adaptive network (DSAN) approach is proposed. Initially, an FEM technique employed to construct model for (target domain), and similarity between simulated data assessed obtain valid samples target domain. Subsequently, time–frequency Markov representation method utilized extract imaging features from samples, which serve as input model. Then, DSAN established facilitate transfer simulation reality, source domain comprising sample set conditions that includes various types of obtained through FEM, containing only limited number normal conditions. The application analysis has demonstrated effectiveness proposed method, achieving classification accuracy 99%. can significantly high-precision diagnostics small size.

Language: Английский

Finite Element Modeling-Assisted Deep Subdomain Adaptation Method for Tool Condition Monitoring DOI Open Access

Jing Cong,

Xin He, Guirong Xu

et al.

Processes, Journal Year: 2025, Volume and Issue: 13(2), P. 545 - 545

Published: Feb. 15, 2025

To reduce the experimental costs associated with tool condition monitoring (TCM) under new cutting conditions, a finite element modeling (FEM)-assisted deep subdomain adaptive network (DSAN) approach is proposed. Initially, an FEM technique employed to construct model for (target domain), and similarity between simulated data assessed obtain valid samples target domain. Subsequently, time–frequency Markov representation method utilized extract imaging features from samples, which serve as input model. Then, DSAN established facilitate transfer simulation reality, source domain comprising sample set conditions that includes various types of obtained through FEM, containing only limited number normal conditions. The application analysis has demonstrated effectiveness proposed method, achieving classification accuracy 99%. can significantly high-precision diagnostics small size.

Language: Английский

Citations

0