Tool Wear Prediction Based on EMD–PSO–BiGRU Hybrid Model

Miaomiao Xin; Sze Song Ngu; Wanzhen Wang; Xiaomei Ni; Ting Wang; Pengpeng Wang; Yuxiang Zhang

doi:10.46604/peti.2026.15987

Authors

Miaomiao Xin Faculty of Engineering, Universiti Malaysia Sarawak, Kota Samarahan, Malaysia
Sze Song Ngu Faculty of Engineering, Universiti Malaysia Sarawak, Kota Samarahan, Malaysia
Wanzhen Wang School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Jinan, China
Xiaomei Ni School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Jinan, China
Ting Wang School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Jinan, China
Pengpeng Wang School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Jinan, China
Yuxiang Zhang School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Jinan, China

DOI:

https://doi.org/10.46604/peti.2026.15987

Keywords:

tool wear, empirical mode decomposition, bidirectional gated recurrent unit, particle swarm optimization

Abstract

To improve milling tool wear prediction accuracy, which is critical for intelligent manufacturing efficiency and cost reduction, a hybrid model based on empirical mode decomposition (EMD), particle swarm optimization (PSO), and bidirectional gated recurrent unit (BiGRU) is proposed. Raw machining signals are decomposed into intrinsic mode functions (IMFs) via EMD; the Pearson correlation coefficient (PCC) is then used to screen wear-related IMFs to eliminate redundancy. Subsequently, PSO is applied to optimize BiGRU parameters, hidden layer neurons, and learning rate, to reduce the risk of local optima. Validated on the PHM2010 dataset, the model increases R² by 4.1%, reduces root mean square error (RMSE) by 13.9%, achieves a mean absolute percentage error (MAPE) of 5.915%, and outperforms improved subtraction-average-based optimizer (ISABO)-optimized BiGRU with 2.7% higher R²and faster convergence. The contributions lie in the EMD–PCC screening strategy and the integrated hybrid model, providing a practical solution for industrial tool wear prediction.

References

J. Kaiser, D. McFarlane, G. Hawkridge, P. André, and P. Leitão, “A Review of Reference Architectures for Digital Manufacturing: Classification, Applicability and Open Issues,” Computers in Industry, vol. 149, article no. 103923, 2023.

S. Zhou and H. Shen, “Study on Deformations of Gold Film Induced by Ultrafast Laser at GHz Burst Mode,” Journal of Manufacturing Processes, vol. 84, pp. 469-480, 2022.

K. S. Keerthika, M. Asritha, R. N. Kumari, K. R. A. Hegde, and G. Talla, “Tool Life Prediction through Vibration Monitoring During Drilling of Nimonic 90,” Sādhanā, vol. 50, no. 4, article no. 273, 2025.

Y. Zhao, H. Hu, C. Song, and Z. Wang, “Predicting Compressive Strength of Manufactured-Sand Concrete Using Conventional and Metaheuristic-Tuned Artificial Neural Network,” Measurement, vol. 194, article no. 110993, 2022.

M. Marani, M. Zeinali, V. Songmene, and C. K. Mechefske, “Tool Wear Prediction in High-Speed Turning of a Steel Alloy Using Long Short-Term Memory Modelling,” Measurement, vol. 177, article no. 109329, 2021.

M. Ertargin, O. Yildirim, and A. Orhan, “Mechanical and Electrical Faults Detection in Induction Motor Across Multiple Sensors with CNN-LSTM Deep Learning Model,” Electrical Engineering, vol. 106, no. 6, pp. 6941–6951, 2024.

H. Liu, P. Li, and Q. Wang, “Short-Term Prediction of Wind Power Based on BKA-CNN-BiGRU-Attention,” Electric Power Systems Research, vol. 253, article no. 112543, 2026.

Z. Lin, Y. Fan, J. Tan, Z. Li, P. Yang, H. Wang, and W. Duan, “Tool Wear Prediction Based on XGBoost Feature Selection Combined with PSO-BP Network,” Scientific Reports, vol. 15, article no. 3096, pp.1-16, 2025.

T. E. Dribin, A. Muraro, C. A. Camargo, P. J. Turner, J. Wang, G. Roberts, et al., “Anaphylaxis Definition, Overview, and Clinical Support Tool: 2024 Consensus Report—A GA2 LEN Project,” Journal of Allergy and Clinical Immunology, vol. 156, no. 2, pp. 406-417.e6, 2025.

H. Zeng, H. J. Cao, and J. X. Dong, “Tool Wear Prediction Method Based on ISABO-IBiLSTM Model,” China Mechanical Engineering, vol. 35, no. 11, pp. 1995-2006, 2024. (in Chinese)

V. Singh, K. Dey, and S. Padmanabhan, “Signal Processing Techniques for Noise Reduction in Industrial Machinery,” Proceedings of 2024 International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET), Indore, India, IEEE, pp. 1-6, 2024.

A. Redekar, H. S. Dhiman, D. Deb, and S. M. Muyeen, “On Reliability Enhancement of Solar PV Arrays Using Hybrid SVR for Soiling Forecasting Based on WT and EMD Decomposition Methods,” Ain Shams Engineering Journal, vol. 15, no. 6, article no. 102716, 2024.

X. Chen, Y. Zhang, G. Ai, L. Wang, H. Zhang, X. Li, et al., “Distance Optimization KNN and EMD Based Lightweight Hardware IP Core Design for EEG Epilepsy Detection,” Microelectronics Journal, vol. 151, article no. 106335, 2024.

S. Sayyad, S. Kumar, A. Bongale, A. Bongale, P. Kamat, S. Patil, and K. Kotecha, “Data-Driven Remaining Useful Life Estimation for Milling Process: Sensors, Algorithms, Datasets, and Future Directions,” IEEE Access, vol. 9, pp. 110255-110286, 2021.

S. Sayyad, S. Kumar, A. Bongale, K. Kotecha, G. Selvachandran, and P. N. Suganthan, “ Tool Wear Prediction Using Long Short-Term Memory Variants and Hybrid Feature Selection Techniques,” The International Journal of Advanced Manufacturing Technology, vol. 121, no. 9-10, pp. 6611-6633, 2022.

A. Rajakannu, K. Vijayalakshmi, S. R. AV, and J. Wekalao, “Airborne Acoustic Emission-Based Intelligent Wear Detection for Spatiotemporal Data in CNC Drill Bits Using CEEMDAN and ConvLSTM,” Sensors and Actuators A: Physical, vol. 396, article no. 117170, 2025.

A. Rajakannu, R. K. P, V. K, and M. Kamarudeen, “Intelligent Fault Diagnosis of Drill Bit Using Digital Twin Assisted Deep Learning Classifiers of MLP, CNN, Hybrid MLP-CNN, and Hybrid CNN-MLP with PCA Algorithm,” 2024 5th International Conference on Computers and Artificial Intelligence Technology (CAIT), IEEE, pp. 552-559, 2024.

S. P. Shuvo, S. P. Shibazee, C. Das, G. Paul, K. Malakar, and J. A. Mahmud, “Twofold Integration Viability of EMD–Hilbert Transform for Optimizing Short‐Term Precipitation Modeling,” IET Signal Processing, vol. 2025, no. 1, article no. 3385508, 2025.

K. A. Shastry and A. Shastry, “Artificial Intelligence Enabled Gait Monitoring for Parkinson’s Disease: An Attention-Augmented BiGRU Approach,” SN Computer Science, vol. 6, no. 8, article no. 961, 2025.

Y. E. Erdoğan and A. Narin, “Time-Frequency-Based Separation of Earthquake and Noise Signals on Real Seismic Data: EMD, DWT and Ensemble Classifier Approaches,” Sensors, vol. 25, no. 21, article no. 6671, 2025.

K. J. Moore, M. Kurt, M. Eriten, D. M. McFarland, L. A. Bergman, and A. F. Vakakis, “Wavelet-Bounded Empirical Mode Decomposition for Measured Time Series analysis,” Mechanical Systems and Signal Processing, vol. 99, pp. 14-29, 2018.

X. Li, B. S. Lim, J. H. Zhou, S. Huang, S. J. Phua, K. C. Shaw, et al., “Fuzzy Neural Network Modelling for Tool Wear Estimation in Dry Milling Operation,” Annual Conference of the Prognostics and Health Management Society, vol. 1, no. 1, pp. 1-11, 2009.

Y. Duan, H. Li, M. He, and D. Zhao, “A BiGRU Autoencoder Remaining Useful Life Prediction Scheme with Attention Mechanism and Skip Connection,” IEEE Sensors Journal, vol. 21, no. 9, pp. 10905-10914, 2021.

W. Wang, S. S. Ngu, M. Xin, R. Liu, Q. Wang, M. Qiu, et al., “Tool Wear Prediction Based on Adaptive Feature and Temporal Attention with Long Short-Term Memory Model,” International Journal of Engineering and Technology Innovation, vol. 14, no. 3, pp. 271-284, 2024.