AE-XGBoost: A Novel Approach for Machine Tool Machining Size Prediction Combining XGBoost, AE and SHAP
To achieve intelligent manufacturing and improve the machining quality of machine tools, this paper proposes an interpretable machining size prediction model combining eXtreme Gradient Boosting (XGBoost), autoencoder (AE), and Shapley additive explanation (SHAP) analysis. In this study, XGBoost was...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/5/835 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850225253971656704 |
|---|---|
| author | Mu Gu Shuimiao Kang Zishuo Xu Lin Lin Zhihui Zhang |
| author_facet | Mu Gu Shuimiao Kang Zishuo Xu Lin Lin Zhihui Zhang |
| author_sort | Mu Gu |
| collection | DOAJ |
| description | To achieve intelligent manufacturing and improve the machining quality of machine tools, this paper proposes an interpretable machining size prediction model combining eXtreme Gradient Boosting (XGBoost), autoencoder (AE), and Shapley additive explanation (SHAP) analysis. In this study, XGBoost was used to establish an evaluation system for the actual machining size of computer numerical control (CNC) machine tools. The XGBoost model was combined with SHAP approximation to effectively capture local and global features in the data using autoencoders and transform the preprocessed data into more representative feature vectors. Grey correlation analysis (GRA) and principal component analysis (PCA) were used to reduce the dimensions of the original data features, and the synthetic minority overstimulation technique of the Gaussian noise regression (SMOGN) method was used to deal with the problem of data imbalance. Taking the actual size of the machine tool as the response parameter, based on the size parameters in the milling process of the CNC machine tool, the effectiveness of the model is verified. The experimental results show that the proposed AE-XGBoost model is superior to the traditional XGBoost method, and the prediction accuracy of the model is 7.11% higher than that of the traditional method. The subsequent SHAP analysis reveals the importance and interrelationship of features and provides a reliable decision support system for machine tool processing personnel, helping to improve processing quality and achieve intelligent manufacturing. |
| format | Article |
| id | doaj-art-a2dff0e2c7474484be48b6b776ac4a94 |
| institution | OA Journals |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-a2dff0e2c7474484be48b6b776ac4a942025-08-20T02:05:24ZengMDPI AGMathematics2227-73902025-03-0113583510.3390/math13050835AE-XGBoost: A Novel Approach for Machine Tool Machining Size Prediction Combining XGBoost, AE and SHAPMu Gu0Shuimiao Kang1Zishuo Xu2Lin Lin3Zhihui Zhang4College of Mechatronics Engineering, Harbin Institute of Technology, Harbin 150006, ChinaCollege of Aeronautical Engineering, Civil Aviation University of China, Tianjin 300300, ChinaCollege of Aeronautical Engineering, Civil Aviation University of China, Tianjin 300300, ChinaCollege of Mechatronics Engineering, Harbin Institute of Technology, Harbin 150006, ChinaBeijing Aerospace Intelligent Manufacturing Technology Development Co., Ltd., Beijing 100028, ChinaTo achieve intelligent manufacturing and improve the machining quality of machine tools, this paper proposes an interpretable machining size prediction model combining eXtreme Gradient Boosting (XGBoost), autoencoder (AE), and Shapley additive explanation (SHAP) analysis. In this study, XGBoost was used to establish an evaluation system for the actual machining size of computer numerical control (CNC) machine tools. The XGBoost model was combined with SHAP approximation to effectively capture local and global features in the data using autoencoders and transform the preprocessed data into more representative feature vectors. Grey correlation analysis (GRA) and principal component analysis (PCA) were used to reduce the dimensions of the original data features, and the synthetic minority overstimulation technique of the Gaussian noise regression (SMOGN) method was used to deal with the problem of data imbalance. Taking the actual size of the machine tool as the response parameter, based on the size parameters in the milling process of the CNC machine tool, the effectiveness of the model is verified. The experimental results show that the proposed AE-XGBoost model is superior to the traditional XGBoost method, and the prediction accuracy of the model is 7.11% higher than that of the traditional method. The subsequent SHAP analysis reveals the importance and interrelationship of features and provides a reliable decision support system for machine tool processing personnel, helping to improve processing quality and achieve intelligent manufacturing.https://www.mdpi.com/2227-7390/13/5/835machine tool processingdimension predictionXGBoostautoencoderSHAP |
| spellingShingle | Mu Gu Shuimiao Kang Zishuo Xu Lin Lin Zhihui Zhang AE-XGBoost: A Novel Approach for Machine Tool Machining Size Prediction Combining XGBoost, AE and SHAP Mathematics machine tool processing dimension prediction XGBoost autoencoder SHAP |
| title | AE-XGBoost: A Novel Approach for Machine Tool Machining Size Prediction Combining XGBoost, AE and SHAP |
| title_full | AE-XGBoost: A Novel Approach for Machine Tool Machining Size Prediction Combining XGBoost, AE and SHAP |
| title_fullStr | AE-XGBoost: A Novel Approach for Machine Tool Machining Size Prediction Combining XGBoost, AE and SHAP |
| title_full_unstemmed | AE-XGBoost: A Novel Approach for Machine Tool Machining Size Prediction Combining XGBoost, AE and SHAP |
| title_short | AE-XGBoost: A Novel Approach for Machine Tool Machining Size Prediction Combining XGBoost, AE and SHAP |
| title_sort | ae xgboost a novel approach for machine tool machining size prediction combining xgboost ae and shap |
| topic | machine tool processing dimension prediction XGBoost autoencoder SHAP |
| url | https://www.mdpi.com/2227-7390/13/5/835 |
| work_keys_str_mv | AT mugu aexgboostanovelapproachformachinetoolmachiningsizepredictioncombiningxgboostaeandshap AT shuimiaokang aexgboostanovelapproachformachinetoolmachiningsizepredictioncombiningxgboostaeandshap AT zishuoxu aexgboostanovelapproachformachinetoolmachiningsizepredictioncombiningxgboostaeandshap AT linlin aexgboostanovelapproachformachinetoolmachiningsizepredictioncombiningxgboostaeandshap AT zhihuizhang aexgboostanovelapproachformachinetoolmachiningsizepredictioncombiningxgboostaeandshap |