Mechanical Engineering Science

A CNN-LSTM-PSO tool wear prediction method based on multi-channel feature fusion

WANGShuo, YUZhenliang, GUOYongqi, LIUXu


In order to achieve predictive maintenance of CNC machining tools and to be able to change tools intelligently before tool wear is at a critical threshold, a CNN-LSTM tool wear prediction model based on particle swarm algorithm (PSO) optimization with multi-channel feature fusion is proposed. Firstly, the raw signals of seven channels of the machining process are collected using sensor technology and processed for noise reduction; secondly, the time-domain, frequency-domain and time-frequency-domain features of each channel signal are extracted, and a sample data set of spatio-temporal correlation of traffic flow is constructed by dimensionality reduction processing and information fusion of the above features; finally, the data set is input to the CNN-LSTM-PSO model for training and testing. The results show that the CNN-LSTM-PSO model can effectively predict tool wear with an average absolute error MAE value of 0.5848, a root mean square error RMSE value of 0.7281, and a coefficient of determination R2 value of 0.9964; and compared with the BP model, CNN model, LSTM model and CNN-LSTM model, its tool wear prediction accuracy improved by 7.56%, 2.60%, 2.98%, and 1.63%, respectively.


feature fusion; CNN-LSTM; tool wear; life prediction

Full Text:



Andis Ābele, Henn Tuherm. Predictions of Cutting Tool Wear of Straight Milled Aspen Wood with Taylor's Equation [J]. Current Journal of Applied Science and Technology, 2016(5):7.

Cynthia Deb, M. Ramesh Nachiappan, M. Elangovan, V. Sugumaran. Fault Diagnosis of a Single Point Cutting Tool using Statistical Features by Random Forest Classifier [J]. Indian Journal of Science and Technology, 2016, 9(33):45-46.

Xu Yanwei, Gui Lin, Xie Tancheng. Intelligent Recognition Method of Turning Tool Wear State Based on Information Fusion Technology and BP Neural Network [J]. Shock and Vibration, 2021(2):55-56.

Alajmi Mahdi, Almeshal Abdullah. Estimation and Optimization of Tool Wear in Conventional Turning of 709M40 Alloy Steel Using Support Vector Machine (SVM) with Bayesian Optimization [J]. Materials,2021, 14(14):23. Wei Weihua, Cong Rui, Li Yuantong. Prediction of tool wear based on GA-BP neural network [J]. Proceedings of the Institution of Mechanical Engineers,2022, 236(12):8-9.

Sarat Babu Mulpur, Babu Rao Thella. Multi-sensor heterogeneous data-based online tool health monitoring in milling of IN718 superalloy using OGM (1, N) model and SVM [J]. Measurement, 2022(199):723-724.

Lee Hojin, Jeong Hyeyun, Koo Gyogwon. Attention RNN Based Severity Estimation Method for Interturn Short-Circuit Fault in PMSMs [J]. IEEE Transactions on Industrial Electronics, 2020(5):7.

Han Sung-Ryeol, Kim Yun-Su. A fault identification method using LSTM for a closed-loop distribution system protective relay [J]. International Journal of Electrical Power and Energy Systems, 2023(148):5-8.

Zhou Yuankai, Wang Zhiyong, Zuo Xue. Identification of wear mechanisms of main bearings of marine diesel engine using recurrence plot based on CNN model [J]. Wear, 2023(6): 520-521.

Ma Kaile, Wang Guofeng, Yang Kai. tool wear monitoring for cavity milling based on vibration singularity analysis and stacked LSTM [J]. The International Journal of Advanced Manufacturing Technology, 2022(120):5-6.

Lim Meng Lip, Derani Mohd Naqib, Ratnam Mani Maran, Yusoff Ahmad Razlan. tool wear prediction in turning using workpiece surface profile images and deep learning neural networks [J]. The International Journal of Advanced Manufacturing Technology, 2022(120):11-12.

Jiahang L, Xu Z. Convolutional neural network based on attention mechanism and BiLSTM for bearing remaining life prediction [J]. Appl Intell. 2021(52):1076 -1091

Stefan Droste, Thomas Jansen, Ingo Wegener. Upper and Lower Bounds for Randomized Search Heuristics in Black-Box Optimization. Electron. Colloquium Comput [J]. Complex, 2003(77):48-48.

Weifeng Lu, Bingyu Cai, Rui Gu. Improved Particle Swarm Optimization Based on Gradient Descent Method [J]. CSAE, 2020(2): 121-126.

Salih Omran, Duffy Kevin Jan. Optimization Convolutional Neural Network for Automatic Skin Lesion Diagnosis Using a Genetic Algorithm [J]. Applied Sciences, 2023,13(5):7.

Zhang Xin, Jiang Yueqiu, Zhong Wei. Prediction Research on Irregularly Cavitied Components Volume Based on Gray Correlation and PSO-SVM [J]. Applied Sciences,2023,13(3):87-89.

Wang Ji, Zhou Jian, Mo Wen-An. Tool life prediction based on multi-source feature PSO-SVR neural network [J]. Journal of Physics: Conference Series, 2022,2366(1):754-756.

Gajera Himanshu K., Nayak Deepak Ranjan, Zaveri Mukesh A.. A comprehensive analysis of dermoscopy images for melanoma detection via deep CNN features [J]. Biomedical Signal Processing and Control, 2023,79(2):46-50.

Ning Zhang, Enping Chen, Yukang Wu, et al. A novel hybrid model integrating residual structure and bi- directional long short- term memory network for tool wear monitoring [J].The International Journal of Advanced Manufacturing Technology , 2022(120):6707-6722

Li Xianwang, Qin Xuejing, Wu Jinxin, et al. tool wear prediction based on convolutional bidirectional LSTM model with improved particle swarm optimization [J]. The International Journal of Advanced Manufacturing Technology, 2022,123(11-12):89-92.

Huimin Chen. A Multiple Model Prediction Algorithm for CNC Machine Wear PHM [J]. International Journal of Prognostics and Health Management, 2011,2(2):78-89.

Li Yifan, Xiang Yongyong, Pan Baisong, et al. A hybrid remaining useful life prediction method for cutting tool considering the wear state [J]. The International Journal of Advanced Manufacturing Technology, 2022(121):5-6.



  • There are currently no refbacks.

Copyright (c) 2023 Shuo WANG, Zhenliang YU, Yongqi GUO, Xu LIU

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.