Tool wear prediction based on XGBoost feature selection combined with PSO-BP network
Abstract To address the challenge of accurately capturing tool wear states in small sample scenarios, this paper proposes a tool wear prediction method that combines XGBoost feature selection with a PSO-BP network. In order to solve the problem of input feature selection and parameter selection in B...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-85694-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585690981859328 |
|---|---|
| author | Zhangwen Lin Yankun Fan Jinling Tan Zhen Li Peng Yang Hua Wang Weiwei Duan |
| author_facet | Zhangwen Lin Yankun Fan Jinling Tan Zhen Li Peng Yang Hua Wang Weiwei Duan |
| author_sort | Zhangwen Lin |
| collection | DOAJ |
| description | Abstract To address the challenge of accurately capturing tool wear states in small sample scenarios, this paper proposes a tool wear prediction method that combines XGBoost feature selection with a PSO-BP network. In order to solve the problem of input feature selection and parameter selection in BP neural network, a double-layer programming model of input feature and parameter selection is established, which is solved by XGBoost and PSO. Initially, vibration and cutting force signals from CNC machining are preprocessed using time-domain segmentation, Hampel filtering, and wavelet denoising. Subsequently, time-domain, frequency-domain, and time–frequency domain features are extracted from the preprocessed data using FFT and wavelet packet decomposition, followed by feature screening for tool wear mapping via Pearson correlation and XGBoost feature importance analysis as model input. Finally, PSO is employed to optimize BPNN parameters. Experimental results show that PSO outperforms other algorithms in training the tool wear prediction model, with XGBoost feature selection reducing model construction time by 57.4% and increasing accuracy by 63.57%, demonstrating superior feature selection capabilities over Decision Tree, Random Fores, Adaboost and Extra Trees. These findings suggest that the proposed method can effectively predict tool wear in real-world CNC machining, contributing to improved production efficiency, reduced tool replacement frequency, and lower maintenance costs, thereby providing valuable insights for industrial applications. |
| format | Article |
| id | doaj-art-1efe4500749e4b169934779de4db72c4 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-1efe4500749e4b169934779de4db72c42025-01-26T12:32:42ZengNature PortfolioScientific Reports2045-23222025-01-0115111610.1038/s41598-025-85694-9Tool wear prediction based on XGBoost feature selection combined with PSO-BP networkZhangwen Lin0Yankun Fan1Jinling Tan2Zhen Li3Peng Yang4Hua Wang5Weiwei Duan6College of Mechanical Engineering, Anhui Institute of Information TechnologyCollege of Mechanical and Power Engineering, China Three Gorges UniversityCollege of Innovation and Entrepreneurship, China Three Gorges UniversityCollege of Mechanical Engineering, Anhui Institute of Information TechnologyCollege of Mechanical Engineering, Anhui Institute of Information TechnologyCollege of Mechanical Engineering, Anhui Institute of Information TechnologyCollege of Mechanical Engineering, Anhui Institute of Information TechnologyAbstract To address the challenge of accurately capturing tool wear states in small sample scenarios, this paper proposes a tool wear prediction method that combines XGBoost feature selection with a PSO-BP network. In order to solve the problem of input feature selection and parameter selection in BP neural network, a double-layer programming model of input feature and parameter selection is established, which is solved by XGBoost and PSO. Initially, vibration and cutting force signals from CNC machining are preprocessed using time-domain segmentation, Hampel filtering, and wavelet denoising. Subsequently, time-domain, frequency-domain, and time–frequency domain features are extracted from the preprocessed data using FFT and wavelet packet decomposition, followed by feature screening for tool wear mapping via Pearson correlation and XGBoost feature importance analysis as model input. Finally, PSO is employed to optimize BPNN parameters. Experimental results show that PSO outperforms other algorithms in training the tool wear prediction model, with XGBoost feature selection reducing model construction time by 57.4% and increasing accuracy by 63.57%, demonstrating superior feature selection capabilities over Decision Tree, Random Fores, Adaboost and Extra Trees. These findings suggest that the proposed method can effectively predict tool wear in real-world CNC machining, contributing to improved production efficiency, reduced tool replacement frequency, and lower maintenance costs, thereby providing valuable insights for industrial applications.https://doi.org/10.1038/s41598-025-85694-9Tool wear predictionXGBoostPSO-BP neural network |
| spellingShingle | Zhangwen Lin Yankun Fan Jinling Tan Zhen Li Peng Yang Hua Wang Weiwei Duan Tool wear prediction based on XGBoost feature selection combined with PSO-BP network Scientific Reports Tool wear prediction XGBoost PSO-BP neural network |
| title | Tool wear prediction based on XGBoost feature selection combined with PSO-BP network |
| title_full | Tool wear prediction based on XGBoost feature selection combined with PSO-BP network |
| title_fullStr | Tool wear prediction based on XGBoost feature selection combined with PSO-BP network |
| title_full_unstemmed | Tool wear prediction based on XGBoost feature selection combined with PSO-BP network |
| title_short | Tool wear prediction based on XGBoost feature selection combined with PSO-BP network |
| title_sort | tool wear prediction based on xgboost feature selection combined with pso bp network |
| topic | Tool wear prediction XGBoost PSO-BP neural network |
| url | https://doi.org/10.1038/s41598-025-85694-9 |
| work_keys_str_mv | AT zhangwenlin toolwearpredictionbasedonxgboostfeatureselectioncombinedwithpsobpnetwork AT yankunfan toolwearpredictionbasedonxgboostfeatureselectioncombinedwithpsobpnetwork AT jinlingtan toolwearpredictionbasedonxgboostfeatureselectioncombinedwithpsobpnetwork AT zhenli toolwearpredictionbasedonxgboostfeatureselectioncombinedwithpsobpnetwork AT pengyang toolwearpredictionbasedonxgboostfeatureselectioncombinedwithpsobpnetwork AT huawang toolwearpredictionbasedonxgboostfeatureselectioncombinedwithpsobpnetwork AT weiweiduan toolwearpredictionbasedonxgboostfeatureselectioncombinedwithpsobpnetwork |