Tool Wear Identification and Monitoring of Hard Alloy End Mills Using an Improved WOA and ConvLSTM
DOI:
https://doi.org/10.15282/ijame.22.4.2025.15.0992Keywords:
WOA, LSTM, ID-CNN, End mill, Wear identification, SVMAbstract
The wear state of carbide end mills directly affects the processing efficiency and quality. Traditional methods (such as Support Vector Machine (SVM)) have problems such as insufficient feature extraction and poor robustness when dealing with high-dimensional nonlinear data. To this end, an SVM classification model optimized by the Whale Optimization Algorithm (WOA) is proposed. The study combines the Convolutional Long Short-Term Memory (ConvLSTM) network and the Attention Mechanism (AM) to construct the wear prediction model (ConvLSTM-AM). Experiments show that the average classification accuracy of SVM-WOA for the four types of wear exceeds 97%, and the classification time is only 1.15 seconds. The prediction accuracy of ConvLSTM-AM in the severe wear stage reaches 98.64%, and the prediction error is significantly lower than that of the comparison models. This method provides an efficient solution for real-time monitoring and intelligent maintenance of tool wear.
References
[1] G. Zheng, W. Chen, Q. Qian, A. Kumar, W. Sun, and Y. Zhou, “TCM in milling processes based on attention mechanism-combined long short-term memory using a sound sensor under different working conditions,” International Journal of Hydromechatronics, vol. 5, no. 3, pp. 243-259, 2022.
[2] Y. Cheng, X. Zhang, G. Zhang, W. Jiang, and B. Li. “Thermal error analysis and modeling for high-speed motorized spindles based on LSTM-CNN,” International Journal of Advanced Manufacturing Technology, vol. 121, no. 5, pp. 3243-3257, 2022.
[3] C. Yang, J. Zhou, E. Li, H. Zhang, M. Wang, and Z. Li. “Milling cutter wear prediction method under variable working conditions based on LRCN,” International Journal of Advanced Manufacturing Technology, vol. 121, no. 3, pp. 2647-2661, 2022.
[4] J. Purohit and R. Dave. “Leveraging deep learning techniques to obtain efficacious segmentation results,” Archives of Advanced Engineering Science, vol. 1, no. 1, pp. 11-26, 2023.
[5] A. Darwish. “A data-driven deep learning approach for remaining useful life in the ion mill etching process,” Sustainable Machine Intelligence Journal, vol. 8, no. 2, pp. 14-34, 2024.
[6] W. Huang, Y. Li, X. Wu, and J. Shen. “The wear detection of mill-grinding tool based on acoustic emission sensor,” The International Journal of Advanced Manufacturing Technology, vol. 124, no. 11, pp. 4121-4130, 2022.
[7] A. S. Pyatykh, A. V. Savilov, and S. A. Timofeev. “Method of tool wear control during stainless steel end milling,” Journal of Friction and Wear, vol. 42, no. 4, pp. 263-267, 2021.
[8] Y. Peng, Q. Song, R. Wang, and Z. Liu. “Intelligent recognition of tool wear in milling based on a single sensor signal The International Journal of Advanced Manufacturing Technology, vol. 124, no. 3, pp. 1077-1093, 2022.
[9] S. Wang, S. Yan, and Y. Sun. “Milling tool condition monitoring for difficult-to-cut materials based on NCAE and IGWO-SVM,” International Journal of Advanced Manufacturing Technology, vol. 129, no. 3, pp. 1355-1374, 2023.
[10] M. Shah, V. Vakharia, R. Chaudhari, J. Vora, D. Y. Pimenov, and K. Giasin. “Tool wear prediction in face milling of stainless steel using singular generative adversarial network and LSTM deep learning models,” International Journal of Advanced Manufacturing Technology, vol. 121, no. 1, pp. 723-736, 2022.
[11] J. S. Nam and W. T. Kwon. “A study on tool breakage detection during milling process using LSTM-autoencoder and Gaussian mixture model,” International Journal of Precision Engineering and Manufacturing, vol. 23, no. 6, pp. 667-675, 2022.
[12] K. Ma, G. Wang, K. Yang, M. Hu, and J. Li. “Tool wear monitoring for cavity milling based on vibration singularity analysis and stacked LSTM,” International Journal of Advanced Manufacturing Technology, vol. 120, no. 5, pp. 4023-4039, 2022.
[13] S. Sivaraman, N. Radhika and M. Abubaker Khan, “Machine Learning-Driven Prediction of Wear Rate and Phase Formation in High Entropy Alloy Coatings for Enhanced Durability and Performance,” IEEE Acces, vol. 13, pp. 33956-33975, 2025.
[14] H. G. Demir and I. Yesilyurt. “A comparison of four machine learning techniques and continuous wavelet transform approach for detection and classification of tool breakage during milling process,” Transactions of the Canadian Society for Mechanical Engineering, vol. 47, no. 1, pp. 26-42, 2022.
[15] S. Chauhan, R. Trehan, R. P. Singh and V. S. Sharma, “Assessment of machining performance for intelligent tool wear prediction using hybrid extreme learning machine,” IEEE Sensors Journal, vol. 24, no. 22, pp. 37915-37922, 2024.
[16] N. Chu, W. Kang, X. Yao, and J. Fu, “Online roundness prediction of grinding workpiece based on vibration signals and support vector machine,” International Journal of Advanced Manufacturing Technology, vol. 126, no. 5, pp. 2733-2743, 2023.
[17] D. Wang, C. Han, L. Wang, X. Li, E. Cai, and P. Zhang, “Surface roughness prediction of large shaft grinding via attentional CNN-LSTM fusing multiple process signals,” International Journal of Advanced Manufacturing Technology, vol. 126, no. 11, pp. 4925-4936, 2023.
[18] J. Sharmila Devi and P. Balasubramanian, “Comparative analysis on recent deep learning techniques for identifying chatter in milling process,” Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3647-3666, 2023.
[19] Y. Quan, C. Liu, Z. Yuan and B. Yan, “Hybrid data augmentation combining screening-based MCGAN and manual transformation for few-shot tool wear state recognition,” IEEE Sensors Journal, vol. 24, no. 8, pp. 12186-12196, 2024.
[20] Y. Liu, S. Yang, T. Sun, and Y. Zhang, “Milling tool wear prediction: optimized long short-term memory model based on attention mechanism,” Ferroelectrics, vol. 607, no. 1, pp. 56-72, 2023.
[21] Y. Meng, Z. Dong, K. -C. Lu, S. Li and C. Shao, “Meta-learning-based domain generalization for cost-effective tool condition monitoring in ultrasonic metal welding,” IEEE Transactions on Industrial Informatics, vol. 21, no. 1, pp. 653-662, 2025.
[22] Q. Hu, B. Su, J. Kong and W. Liu, “Adaptive wavelet convolution stochastic analysis graph neural network for remaining useful life prediction,” IEEE Sensors Journal, vol. 25, no. 11, pp. 19428-19441, 2025.
[23] H. Sümbül, “A Novel Mems and Flex Sensor-Based Hand Gesture Recognition and Regenerating System Using Deep Learning Model,” IEEE Acces, vol. 12, pp. 133685-133693, 2024.
[24] K. Ouyang, P. Hu, J. Liao and L. Yang, “Measurement method of 3-D rotation angle of spherical joint based on neural network and magnetic effect,” IEEE Sensors Journal, vol. 24, no. 16, pp. 26866-26876, 2024.
[25] C. Ren, B. Jiang and N. Lu, “Federated learning with potential partnership identification for accurate prediction in flexible manufacturing system,” IEEE Transactions on Reliability, vol. 74, no. 2, pp. 2549-2560, 2025.
[26] D. -M. Shi, T. Huang, X. -M. Zhang and H. Ding, “Superresolution restoration of cutting forces in thin-walled milling with a diffusion model,” IEEE/ASME Transactions on Mechatronics, vol. 30, no. 2, pp. 1447-1458, 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
