Remaining Useful Life Prediction of Milling Tool Based on Improved PSO-MultiAM-BiLSTM

Xiaomei Ni; David Chua Sing Ngie; Wanzhen Wang; Miaomiao Xin; Qiu Man; Liangyu Tian; Jingzhe Sun

doi:10.46604/aiti.2025.15175

Authors

Xiaomei Ni Faculty of Engineering, Universiti Malaysia Sarawak (UNIMAS), Sarawak, Malaysia
David Chua Sing Ngie Faculty of Engineering, Universiti Malaysia Sarawak (UNIMAS), Sarawak, Malaysia
Wanzhen Wang School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Shandong, China
Miaomiao Xin School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Shandong, China
Qiu Man School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Shandong, China
Liangyu Tian School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Shandong, China
Jingzhe Sun School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Shandong, China

DOI:

https://doi.org/10.46604/aiti.2025.15175

Keywords:

MultiAM, PSO algorithm, BiLSTM, RUL

Abstract

To improve the accuracy of remaining useful life (RUL) prediction for milling tools, this study proposes an enhanced PSO-MultiAM-BiLSTM model integrating particle swarm optimization (PSO), multi-head attention mechanism (MultiAM), and bidirectional long short-term memory (BiLSTM). The model captures key information in input sequences, alleviating early feature attenuation in BiLSTM from “chain propagation.” A logarithmic decreasing strategy adjusts PSO inertia weights, balancing global and local searches while optimizing BiLSTM parameters. Validated on the PHM2010 dataset, the model attains an average coefficient of determination of 0.97, with average root-mean-square error and mean absolute error of 0.062 and 0.045, improving prediction accuracy by 9.64% and 4.06% over MultiAM-BiLSTM and PSO-AM-BiLSTM, respectively. Such a result attests to the effective extraction of degradation features of tools and provides a valuable reference for predicting the RUL of milling tools.

References

J. Karandikar, T. Schmitz, and S. Smith, “Physics-Guided Logistic Classification for Tool Life Modeling and Process Parameter Optimization in Machining,” Journal of Manufacturing Systems, vol. 59, pp. 522-534, 2021.

X. Liu, S. Liu, X. Li, B. Zhang, C. Yue, and S. Y. Liang “Intelligent Tool Wear Monitoring Based on Parallel Residual and Stacked Bidirectional Long Short-Term Memory Network,” Journal of Manufacturing Systems, vol. 60, pp. 608-619, 2021.

N. K. Singh, R. K. Rathore, A. K. Sinha, and H. Narayan, “Multiobjective Optimization of Process Parameter Subjected to End Milling Process of AA7075 Alloy Through TOPSIS Method,” AIP Conference Proceedings, vol. 3111, no. 1, article no. 060004, 2024.

D. Han, J. Yu, and D. Tang, “An HDP-HMM Based Approach for Tool Wear Estimation and Tool Life Prediction,” Quality Engineering, vol. 33, no. 2, pp. 208-220, 2020.

N. Brili, M. Ficko, and S. Klančnik, “Tool Condition Monitoring of the Cutting Capability of a Turning Tool Based on Thermography,” Sensors, vol. 21, no. 19, article no. 6687, 2021.

L. Wu, K. Sha, Y. Tao, B. Ju, and Y. Chen, “A Hybrid Deep Learning Model as the Digital Twin of Ultra-Precision Diamond Cutting for In-Process Prediction of Cutting-Tool Wear,” Applied Sciences, vol. 13, no. 11, article no. 6675, 2023.

W. X. Yan, W. Pin, and L. He, “Reliability Prediction of CNC Machine Tool Spindle Based on Optimized Cascade Feedforward Neural Network,” IEEE Access, vol. 9, pp. 60682-60688, 2021.

P. Ünal, B. U. Deveci, and A. M. Özbayoğlu, “A Review: Sensors Used in Tool Wear Monitoring and Prediction,” International Conference on Mobile Web and Intelligent Information Systems, pp. 193-205, 2022.

C. Shi, B. Luo, S. He, K. Li, H. Liu, and B. Li, “Tool Wear Prediction via Multidimensional Stacked Sparse Autoencoders with Feature Fusion,” IEEE Transactions on Industrial Informatics, vol. 16, no. 8, pp. 5150-5159, 2020.

Q. An, Z. Tao, X. Xu, M. El Mansori, and M. Chen, “A Data-Driven Model for Milling Tool Remaining Useful Life Prediction with Convolutional and Stacked LSTM Network,” Measurement, vol. 154, article no. 107461, 2020.

M. Wang, J. Zhou, J. Gao, Z. Li, and E. Li, “Milling Tool Wear Prediction Method Based on Deep Learning under Variable Working Conditions,” IEEE Access, vol. 8, pp. 140726-140735, 2020.

S. Wang, Z. Yu, G. Xu, and F. Zhao, “Research on Tool Remaining Life Prediction Method Based on CNN-LSTM-PSO,” IEEE Access, vol. 11, pp. 80448-80464, 2023.

J. Yao, B. Lu, and J. Zhang, “Tool Remaining Useful Life Prediction Using Deep Transfer Reinforcement Learning Based on Long Short-Term Memory Networks,” The International Journal of Advanced Manufacturing Technology, vol. 118, no. 3-4, pp. 1077-1086, 2022.

B. Li and X. Tian, “An Effective PSO-LSSVM-Based Approach for Surface Roughness Prediction in High-Speed Precision Milling,” IEEE Access, vol. 9, pp. 80006-80014, 2021.

Y. Ge, J. Zhang, G. Song, and K. Zhu, “An Effective LSSVM-Based Approach for Milling Tool Wear Prediction,” The International Journal of Advanced Manufacturing Technology, vol. 126, no. 9-10, pp. 4555-4571, 2023.

J. W. Li, C. B. Liu, H. Guo, and N. Lyu, “Tool Life Prediction Based on PSO-RBF Neural Network,” Computer Systems Applications, vol. 31, no. 1, pp. 309-314, 2022. (In Chinese)

P. Wei, R. Li, X. Liu, H. Gao, M. Dai, Y. Zhang, et al., “Research on Tool Wear State Identification Method Driven by Multi-Source Information Fusion and Multi-Dimension Attention Mechanism,” Robotics and Computer-Integrated Manufacturing, vol. 88, article no. 102741, 2024.

G. Wang and F. Zhang, “A Sequence-to-Sequence Model with Attention and Monotonicity Loss for Tool Wear Monitoring and Prediction,” IEEE Transactions on Instrumentation and Measurement, vol. 70, article no. 3525611, 2021.

C. Dong and J. Zhao, “An Augmented AutoEncoder with Multi-Head Attention for Tool Wear Prediction in Smart Manufacturing,” IEEE Access, vol. 12, pp. 79128-79137, 2024.

G. Sateesh Babu, P. Zhao, and X. L. Li, “Deep Convolutional Neural Network Based Regression Approach for Estimation of Remaining Useful Life,” International Conference on Database Systems for Advanced Applications, pp. 214-228, 2016.

C. Zhao, X. Huang, Y. Li, and M. Yousaf Iqbal, “A Double-Channel Hybrid Deep Neural Network Based on CNN and BiLSTM for Remaining Useful Life Prediction,” Sensors, vol. 20, no. 24, article no. 7109, 2020.

B. Li, M. Han, X. Zhang, H. Luan, and S. Sun, “Research on the Prediction Method of Remaining Tool Life Based on GASF-LSTM-Attention,” 10th International Conference on Computer and Communications, pp. 1422-1427, 2024.