Journal of Applied Science and Engineering

Published by Tamkang University Press

ESCI jase impact factor scopus logo open access rate of Scopus journal

Deep Learning-Driven Adaptive Machining Parameter Optimization for High-Precision CNC Milling

 2026

 Volume 31

Xiaoli Qu

Zhengzhou Technical College, No. 081, Zhengshang Road, Zhengzhou City, China

Received: January 21, 2026
Accepted: March 9, 2026
Publication Date: April 12, 2026

上傳圖片

Overall architecture of the proposed framework

 Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation:  BibTeX | https://doi.org/10.6180/jase.202608_31.067  

Download PDF

To address the limitations of single-modal data and low real-time performance in traditional anomaly diagnosis for CNC turning processes, this paper proposes a novel framework integrating adaptive multi-modal data fusion and lightweight graph neural network (GNN) for real-time anomaly diagnosis. First, multi-modal data (vibration, spindle current, and cutting force) are collected and preprocessed to extract time-frequency domain features. A mutual information-based graph construction method is designed to model the intrinsic correlations between multi-modal features, converting non-Euclidean feature data into structured graph data. Then, an event-driven lightweight GNN (EL-GNN) is proposed, which adopts a hierarchical propagation mechanism to reduce redundant computations and realizes millisecond-level inference. A cross-attention fusion module is embedded in the GNNto dynamically assign weights to different modal features, enhancing the robustness to noise. Experiments are conducted on a self-built CNC turning test platform and the public tool wear dataset. Results show that the proposed framework achieves an anomaly diagnosis accuracy of 98.73%, a recall rate of 98.51%, and a P99 inference latency of 28.3 ms , outperforming traditional machine learning methods and deep learning models by 3.2%−8.9% in accuracy. This framework provides a reliable solution for intelligent predictive maintenance in CNC turning processes, balancing diagnostic accuracy and real-time performance.

Keywords: Deep Learning-Driven; Adaptive Machining; Parameter Optimization; High-Precision CNC Milling

  1. [1] P. Kailomsom, P. Nasawat, W. Khunthirat, and W. Phuangpornpitak, (2025) “A hybrid method based on BWM and TOPSIS-LP model to assess computer numerical control machines” Engineering Access 11(1): 108–118. DOI: 10.14456/mijet.2025.9.
  2. [2] I. E. Oiye, P. Poojar, E. Qian, J. T. Vaughan Jr, and S. Geethanath, (2025) “A standalone and cost-effective MR-compatible computer numerical control machine for simultaneous, multi-parameter mapping” Measurement Science and Technology 36(4): 045902. DOI: 10.1088/1361-6501/adbb09.
  3. [3] Z. A. Aldeeb and A. M. Hwas, (2025) “Design and Implementation of Computer Numerical Controlled Milling Machine for Printed Circuit Board Fabrication” African Journal of Advanced Pure and Applied Sciences 4(3): 116–125. DOI: 10.65418/ajapas.v4i3.1343.
  4. [4] J. Singh, A. Singh, H. Singh, and P. Doyon-Poulin, (2025) “Implementation and evaluation of a smart machine monitoring system under industry 4.0 concept” Journal of Industrial Information Integration 43: 100746. DOI: 10.1016/j.jii.2024.100746.
  5. [5] S. Yin, H. Li, A. A. Laghari, L. Teng, T. R. Gadekallu, and A. Almadhor, (2024) “FLSN-MVO: edge computing and privacy protection based on federated learning Siamese network with multi-verse optimization algorithm for industry 5.0” IEEE Open Journal of the Communications Society 6: 3443–3458. DOI: 10.1109/OJCOMS.2024.3520562.
  6. [6] J. Sun, D. Wang, Z. Liu, C. Qiu, H. Liu, G. Sa, and J. Tan, (2025) “Tool digital twin based on knowledge embedding for precision CNC machine tools: Wear prediction for collaborative multi-tool” Journal of Manufacturing Systems 80: 157–175. DOI: 10.1016/j.jmsy.2025.02.021.
  7. [7] A. D. Yewle, L. Mirzayeva, and O. Karakuş, (2025) “Multi-modal data fusion and deep ensemble learning for accurate crop yield prediction” Remote Sensing Applications: Society and Environment 38: 101613. DOI: 10.1016/j.rsase.2025.101613.
  8. [8] X. Wu and A. He, (2025) “Multimodal information fusion and artificial intelligence approaches for sustainable computing in data centers” Pattern Recognition Letters 189: 17–22. DOI: 10.1016/j.patrec.2024.12.006.
  9. [9] Z. Gao, Y. Wang, X. Li, and J. Yao, (2024) “Twins transformer: rolling bearing fault diagnosis based on cross-attention fusion of time and frequency domain features” Measurement Science and Technology 35(9): 096113. DOI: 10.1088/1361-6501/ad53f1.
  10. [10] J. Yu, L. Zhao, S. Yin, and M. Ivanović, (2024) “News recommendation model based on encoder graph neural network and bat optimization in online social multimedia art education” Computer Science and Information Systems 21(3): 989–1012. DOI: 10.2298/CSIS231225025Y.
  11. [11] J. Wu, C. Ni, H. Wang, and J. Chen, (2025) “Graph neural networks for efficient clock tree synthesis optimization in complex SoC designs” Applied and Computational Engineering 150: 101–111. DOI: 10.54254/2755-2721/2025.22281.
  12. [12] J. Dai, Z. Zhang, Z. Liu, and W. Yuan, (2025) “Improved Detection of Mixed Pesticide Solution Concentrations Using Deep Learning with Segmented Stride 1D-CNN and Color Rendering Index Features” Journal of the ASABE 68(3): 353–363. DOI: 10.13031/ja.16122.
  13. [13] J. Choi, Z. Xiong, and K. Kang, (2025) “Long short-term memory-based computerized numerical control machining center failure prediction model” Mathematics 13(7): 1093. DOI: 10.3390/math13071093.
  14. [14] M. Ahmadzadeh, S. M. Zahrai, and M. Bitaraf, (2025) “An integrated deep neural network model combining 1D CNN and LSTM for structural health monitoring utilizing multisensor time-series data” Structural Health Monitoring 24(1): 447–465. DOI: 10.1177 / 14759217241239041.
  15. [15] R. Li, H. Shen, Q. Zhang, and H. Duan, (2025) “An edge-enhanced graphSAGE-based intrusion detection model for the internet of things” Cluster Computing 28(5): 309. DOI: 10.1007/s10586-025-05100-x.
  16. [16] D. Wu, Z. Li, and T. Mitra. “Inkstream: Instantaneous GNN Inference on Dynamic Graphs via Incremental Update”. In: 2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE. 2025, 1273–1285. DOI: 10.1109/IPDPS64566.2025.00115.
  17. [17] L. Teng, H. Li, and Y. Si, (2025) “Neural Tensor Network And Adaptive Graph Convolution For Sports” Journal of Applied Science and Engineering 29(6): 1483–1491. DOI: 10.6180/jase.202606_29(6).0015.