刀具磨耗在生產效率和經濟考量中有著至關重要的影響，在實際生產應用中，為了保持穩定生產，採用恆定的切削參數，但即使在相同的切削條件下，刀具磨耗仍然具有高度變異性，過度或不足的刀具磨耗都會顯著降低加工經濟性。為了應對製程中不拆刀的情況、適應多樣化幾何產品以及刀具磨耗控制的這些挑戰，本研究開發了實用的刀具磨耗預測模型，提前判斷切削刀具的磨耗狀況，並提出一種新穎的方法來建立切削參數調整模組，以控制刀具磨耗，達到刀具磨耗變異性的控制。這種方法能夠在刀具尚未加工完畢，於加工中途即時做出更好的決策。在車削過程中，通過Hilbert變換處理收集到的主軸電流訊號以增強訊號，這使得觀察和分析訊號的主要特徵變得更加容易，隨後對每切削道次進行分段分析。從每個訊號段中提取特徵並進行特徵選取最佳化模型的預測性能，作為LSTM 模型的輸入矩陣，用於預測每次刀具通過後最終的磨耗情況。這種分段方法有助於開發適合不同幾何形狀的模型，並且模型的單元可以根據切削道次進行調整，而不必考慮不同零件之間時間間隔的變化。本研究所提出之方法進行了三個案例驗證，其中案例1 為外徑車削，而案例2 及3 為輪廓車削，三個案例分別達到5.80%、8.02%及15.52%的刀具磨耗預測誤差，而自主切削參數調整方法經實驗結果驗證平均值分別從187.47 μm、180.33 μm 及275.1 μm 改善至205.60 μm、211.33 μm 及199.13μm，更接近200μm 的刀具磨耗極限預設值，且四分位距分別自30.75 μm、43.5 μm 及84.8 μm 改善至24.5 μm、25.5 μm 及41.75 μm。實驗結果顯示此方法可提供準確的刀具磨耗預測，並在製程中進行自主切削參數調整以控制刀具磨耗，使加工結束時的刀具磨耗接近使用者所自行設定之目標。由於過程中不需拆刀量測且可應用在不同之工件幾何上，本研究所提出之方法也更實用於工業中。

The purpose of this study is to develop a practical tool wear prediction model to address challenges in tool wear control and autonomous cutting parameter regulation in turning operations. Tool wear is crucial for production efficiency and economic considerations. This study aims to proactively forecast tool wear and optimize tool life and production efficiency. Spindle current and cutting tool vibration signals collected during turning were processed using the Hilbert transform to enhance signal features, followed by segment analysis for each cutting pass. These features were used as inputs for the Long Short-Term Memory (LSTM) model to predict final tool wear after each pass. The segmented approach allows the model to adapt to various geometries. The method was validated through three case studies: Case 1 straight turning and Cases 2 and 3 profile turning. Prediction errors for tool wear were 5.80%, 8.02%, and 15.52%, respectively. The study proposes an innovative Cutting Parameter Regulation (CPR) method allowed the tool to reach the tool wear limit by the end of the operation. Additionally, the interquartile range of tool wear distribution improved from 30.75 μm, 43.5 μm, and 84.8 μm to 24.5 μm, 25.5 μm, and 41.75 μm, respectively. Results indicate this method effectively adapts to different geometries, provides accurate tool wear prediction, and supports autonomous cutting parameter regulation, aligning final tool wear with user-defined goals and controlling variability. These results enhance production monitoring and provide valuable research insights.

Taylor FW (1907) On the Art of Cutting Metals. Transactions of ASME 28:70-350.
L. Ráczkövi, Ráczkövi L (2010) Tool Life of Cutting Tools in Hard Turning. Hungarian Journal of Industrial Chemistry 38(2):133-136. https://doi.org/10.1515/289.
Sardiñas RQ, Santana MR, Brindis EA (2006) Genetic Algorithm-Based Multi-Objective Optimization of Cutting Parameters in Turning Processes. Engineering Applications of Artificial Intelligence 19:127-133. https://doi.org/10.1016/j.engappai.2005.06.007.
Soori M, Arezoo B, Dastres R (2023) Machine Learning and Artificial Intelligence in CNC Machine Tools: A Review. Sustainable Manufacturing and Service Economics. https://doi.org/10.1016/j.smse.2023.100009.
Wu X, Liu Y, Zhou X, Mou A (2019) Automatic Identification of Tool Wear Based on Convolutional Neural Network in Face Milling Process. Sensors 19:1-17.
Ambadekar PK, Choudhari CM (2020) CNN-Based Tool Monitoring System for Predicting the Life of Cutting Tools. SN Applied Sciences 2:1-11.
Gouarir A, Martínez-Arellano G, Terrazas G, Benardos P, Ratchev S (2018) In-process Tool Wear Prediction System Based on Machine Learning Techniques and Force Analysis. Procedia CIRP 77:501-504.
Alajmi MS, Almeshal AM (2021) Estimation and Optimization of Tool Wear in Conventional Turning of 709M40 Alloy Steel Using Support Vector Machine (SVM) with Bayesian Optimization. Materials 14:1-19.
Shi D, Nabil NG (2011) Tool Wear Prediction Based on Wavelet Transform and Support Vector Machine. In Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics (ICINCO), Jul 28 - Jul 31, 2011, Noordwijkerhout, The Netherlands: 479-485.
Wiciak-Pikula M, Felusiak A, Twardowski P (2020) Artificial Neural Network models for tool wear prediction during Aluminium Matrix Composite milling. 2020 IEEE 7th International Workshop on Metrology for AeroSpace (MetroAeroSpace), June 22 - June 24, 2020, Pisa, Italy: 255-259.
Twardowski P, Wiciak-Pikuła M (2019) Prediction of Tool Wear Using Artificial Neural Networks during Turning of Hardened Steel. Materials 12:1-15.
Bagga PJ, Makhesana MA, Patel HD, Patel KM (2021) Indirect Method of Tool Wear Measurement and Prediction Using ANN Network in Machining Processes. Materials Today: Proceedings 44:1549-1554.
Marani M, Zeinali M, Kouam J, Songmene V, Mechefske CK (2020) Prediction of Cutting Tool Wear During a Turning Process Using Artificial Intelligence Techniques. International Journal of Advanced Manufacturing Technology 111:505-515. https://doi.org/10.1007/s00170-020-06144-6.
Rizal M, Ghani JA, Nuawi MZ, Haron CHC (2013) Online Tool Wear Prediction System in Turning Processes Using an Adaptive Neuro-Fuzzy Inference System. Applied Soft Computing 13:1960-1968. https://doi.org/10.1016/j.asoc.2012.11.043.
Liu X, Liu S, Li X, Zhang B, Yue C, Liang SY (2021) Intelligent Tool Wear Monitoring Based on Parallel Residual and Stacked Bidirectional Long Short-Term Memory Network. Journal of Manufacturing Systems 60:608-619. https://doi.org/10.1016/j.jmsy.2021.06.006.
Bagri S, Manwar A, Varghese A, Mujumdar S, Joshi SS (2021) Tool Wear and Remaining Useful Life Prediction in Micro-Milling along Complex Tool Paths Using Neural Networks. Journal of Manufacturing Processes 71:679-698. https://doi.org/10.1016/j.jmapro.2021.09.055.
Wang M, et al. (2020) Milling Tool Wear Prediction Method Based on Deep Learning Under Variable Working Conditions. IEEE Access 8:140726-140735. https://doi.org/10.1109/ACCESS.2020.3010378.
Masalimov KA, Munasypov RA (2020) Diagnostic of the State of the Cutting Tool of Metal-cutting Machines Using Bidirectional Recurrent Neural Networks with a Long Short-term Memory. 2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV), December 13 - December 15, 2020, Shenzhen, China: 1093-1097. https://doi.org/10.1109/ICARCV50220.2020.9247605.
Li B, Liu T, Liao J, Feng C, Yao L, Zhang J (2023) Non-Invasive Milling Force Monitoring Through Spindle Vibration with LSTM and DNN in CNC Machine Tools. Measurement. https://doi.org/10.1016/j.measurement.2023.112554.
Kim G, Yang SM, Kim DM, Choi JG, Lim S, Park HW (2024) Developing a Deep Learning-Based Uncertainty-Aware Tool Wear Prediction Method Using Smartphone Sensors for the Turning Process of Ti-6Al-4V. Journal of Manufacturing Systems 76:133-157. https://doi.org/10.1016/j.jmsy.2024.07.010.
Warke V, Kumar S, Bongale A, Kotecha K (2024) Robust Tool Wear Prediction Using Multi-Sensor Fusion and Time-Domain Features for the Milling Process Using Instance-Based Domain Adaptation. Knowledge-Based Systems 288:111454. https://doi.org/10.1016/j.knosys.2024.111454.
Cheng Y, Lu M, Gai X, Guan R, Zhou S, Xue J (2024) Research on Multi-Signal Milling Tool Wear Prediction Method Based on GAF-ResNext. Robotics and Computer-Integrated Manufacturing 85:102634. https://doi.org/10.1016/j.rcim.2023.102634.
Peng D, Li H (2024) Intelligent Monitoring of Milling Tool Wear Based on Milling Force Coefficients by Prediction of Instantaneous Milling Forces. Mechanical Systems and Signal Processing 208:111033. https://doi.org/10.1016/j.ymssp.2023.111033.
Kim G, Yang SM, Kim DM, Kim S, Choi JG, Ku M, Lim S, Park HW (2023) Bayesian-Based Uncertainty-Aware Tool-Wear Prediction Model in End-Milling Process of Titanium Alloy. Applied Soft Computing 148:110922. https://doi.org/10.1016/j.asoc.2023.110922.
Marani M, Zeinali M, Songmene V, Mechefske CK (2021) Tool Wear Prediction in High-Speed Turning of a Steel Alloy Using Long Short-Term Memory Modelling. Measurement 177:109329. https://doi.org/10.1016/j.measurement.2021.109329.
Tao Z, An Q, Liu G, Chen M (2019) A Novel Method for Tool Condition Monitoring Based on Long Short-Term Memory and Hidden Markov Model Hybrid Framework in High-Speed Milling Ti-6Al-4V. International Journal of Advanced Manufacturing Technology 105:3165-3182. https://doi.org/10.1007/s00170-019-04589-1.
Kerboua A, Metatla A, Kelaiaia R, Batouche M (2018) Real-Time Safety Monitoring in the Induction Motor Using Deep Hierarchic Long Short-Term Memory. International Journal of Advanced Manufacturing Technology 99:2245-2255. https://doi.org/10.1007/s00170-018-2607-4.
Hao G, Zhu K (2020) Pyramid LSTM Auto-encoder for Tool Wear Monitoring. 2020 16th IEEE International Conference on Automation Science and Engineering (CASE), August 20 - August 21, 2020, Hong Kong, China. IEEE.
Chinomona B, Chung C, Wang P (2022) Pass-Wise Tool Wear Prediction in Turning Based on Long Short-Term Memory Algorithm Using Current Signals. Proceedings of the ASME 2022 17th International Manufacturing Science and Engineering Conference (MSEC2022), June 27-July 1, 2022, West Lafayette, Indiana, USA, Paper No. MSEC2022-85339.
Liu X, Liu S, Li X, Zhang B, Yue C, Liang YS (2021) Intelligent Tool Wear Monitoring Based on Parallel Residual and Stacked Bidirectional Long Short-Term Memory Network. Journal of Manufacturing Systems 60:608-619.
An Q, Tao Z, Xu X, Mohamed E, Chen M (2020) A Data-Driven Model for Milling Tool Remaining Useful Life Prediction with Convolutional and Stacked LSTM Network. Measurement 154:608-619.
Lee J, Choi HJ, Nam J, Jo SB, Kim M, Lee SW (2017) Development and Analysis of an Online Tool Condition Monitoring and Diagnosis System for a Milling Process and Its Real-Time Implementation. Journal of Mechanical Science and Technology 31(12):5695-5703. https://doi.org/10.1007/s12206-017-1110-4.
Zou Z, Lin Y, Lin D, Gu F, Ball AD (2021) Online Tool Condition Monitoring of CNC Turnings based on Motor Current Signature Analysis. Proceedings of the 26th International Conference on Automation & Computing, University of Portsmouth, Portsmouth, UK.
Zhang Y, Zhu K, Duan X, Li S (2021) Tool Wear Estimation and Life Prognostics in Milling: Model Extension and Generalization. Mechanical Systems and Signal Processing 155:107617. https://doi.org/10.1016/j.ymssp.2021.107617.
Rad JS, Hosseini E, Zhang Y, Chen C (2013) Online Tool Wear Monitoring and Estimation Using Power Signals and S-Transform. 2013 Conference on Control and Fault-Tolerant Systems, October 09 - October 11, 2013, Nice, France, IEEE: 234-238. https://ieeexplore.ieee.org/document/6707360.
Wang C, Huang M, Chung TT, Young HT, Li KM (2017) Tool Condition Monitoring with Current Signals for a Low-power Spindle. Proceedings of the 2017 IEEE International Conference on Applied System Innovation, May 13 - May 17, 2017, Sapporo, Japan, IEEE: 686-689. https://ieeexplore.ieee.org/document/8140659.
Cao H, Zhou K, Chen X (2015) Chatter Identification in End Milling Process Based on EEMD and Nonlinear Dimensionless Indicators. International Journal of Machine Tools and Manufacture 92:52-59. https://doi.org/10.1016/j.ijmachtools.2015.03.002.
Zheng X, Arrazola P, Perez R, Echebarria D, Kiritsis D, Aristimuño P, Sáez-de-Buruaga M (2023) Exploring the Effectiveness of Using Internal CNC System Signals for Chatter Detection in Milling Process. Mechanical Systems and Signal Processing 185:109812. https://doi.org/10.1016/j.ymssp.2022.109812.
Ninevski D, Thaler J, O'Leary P, Klünsner T, Mücke M, Hanna L, Teppernegg T, Treichler M, Peissl P, Czettl C (2022) Computational Methods for the Detection of Wear and Damage to Milling Tools. Journal of Manufacturing Processes 82:78-87. https://doi.org/10.1016/j.jmapro.2022.07.030.
ISO 3685-1993. (1993). ISO 3685-1993: Tool Life Testing with Single-Point Turning Tools. [Online]. Available: https://www.iso.org/standard/9151.html
Cao M, Zhou C, Li KM (2021) Research on the Relationship Between Workpiece Surface Machining Quality and Turning Tool Wear. J Phys Conf Ser 2029:13-15.
Liu C, Li Y, Hua J, Lu N, Mou W (2018) Real-Time Cutting Tool State Recognition Approach Based on Machining Features in NC Machining Process of Complex Structural Parts. International Journal of Advanced Manufacturing Technology 97:229-241. https://doi.org/10.1007/s00170-018-1916-y.
Sun H, Liu Y, Pan J, Zhang J, Li W (2020) Enhancing Cutting Tool Sustainability Based on Remaining Useful Life Prediction. Journal of Cleaner Production 244:1-10. https://doi.org/10.1016/j.jclepro.2019.118794.
Trent EM, Wright RK (2000) Metal Cutting, 4th ed., Butterworth-Heinemann, Woburn, MA, USA.
Kuntoglu M, Aslan A, Pimenov DY, Usca UA, Salur E, Gupta MK, Mikolajczyk T, Giasin K, Kapłonek W, Sharma S (2021) A Review of Indirect Tool Condition Monitoring Systems and Decision-Making Methods in Turning: Critical Analysis and Trends. Sensors 21(1):108. https://dx.doi.org/10.3390/s21010108.
Mehta S, Singh RA, Mohata Y, Kiran MB (2019) Measurement and Analysis of Tool Wear Using Vision System. 2019 IEEE 16th India Council International Conference (INDICON): 45-49. https://doi.org/10.1109/INDICON47235.2019.9036789.
Mohanta N, Singh RK, Sharma AK (2020) Online Monitoring System for Tool Wear and Fault Prediction Using Artificial Intelligence. 2020 International Conference on Contemporary Computing and Applications (IC3A), February 05 - February 07, 2020, Lucknow, India: 310-314. https://doi.org/10.1109/IC3A48958.2020.233319.
Mikołajczyk T, Nowicki K, Kłodowski A, Pimenov DY (2017) Neural Network Approach for Automatic Image Analysis of Cutting Edge Wear. Mechanical Systems and Signal Processing 88:100-110. https://doi.org/10.1016/j.ymssp.2016.11.026.
Mikołajczyk T, Nowicki K, Bustillo A, Pimenov DY (2018) Predicting Tool Life in Turning Operations Using Neural Networks and Image Processing. Mechanical Systems and Signal Processing 104:503-513. https://doi.org/10.1016/j.ymssp.2017.11.022.
Yan B, Zhu L, Dun Y (2021) Tool Wear Monitoring of TC4 Titanium Alloy Milling Process Based on Multi-channel Signal and Time-dependent Properties by Using Deep Learning. Journal of Manufacturing Systems 61:495-508. https://doi.org/10.1016/j.jmsy.2021.09.017.
Swain S, Panigrahi I, Sahoo AK, Panda A (2020) Adaptive Tool Condition Monitoring System: A Brief Review. Materials Today Proceedings 23:474-478. https://doi.org/10.1016/j.matpr.2019.05.386.
Kuntoğlu M, Aslan A, Sağlam H, Pimenov DY, Giasin K, Mikolajczyk T (2020) Optimization and Analysis of Surface Roughness, Flank Wear and 5 Different Sensorial Data via Tool Condition Monitoring System in Turning of AISI 5140. Sensors 20:4377. https://doi.org/10.3390/s20164377.
Wang XB, Li LL, Zhao CY (2021) Experimental Study on Influence of Vibration Direction on Tool Wear and Surface Morphology in Ultrasonic Milling of Titanium Alloy. 2020 15th Symposium on Piezoelectricity, Acoustic Waves and Device Applications (SPAWDA), April 16 - April 19, 2021, Zhengzhou, Henan Province, China: 583-587. https://doi.org/10.1109/SPAWDA51471.2021.9445444.
Nie Z, Li F, Li J, Hao H, Lin Y, Ma H (2024) Baseline-free Structural Damage Detection Using PCA-Hilbert Transform with Limited Sensors. Journal of Sound and Vibration 568:117966. Accessed 28 July 2023. https://doi.org/10.1016/j.jsv.2023.117966.
Bhuiyan MSH, Choudhury IA (2014) Review of Sensor Applications in Tool Condition Monitoring in Machining. Comprehensive Materials Processing 13:539-569. https://doi.org/10.1016/B978-0-08-096532-1.01330-3.
Wang L, Gao RX (2006) Condition Monitoring and Control for Intelligent Manufacturing. Springer, London, UK.
Cheng Y, Hu K, Wu J, Zhu H, Shao X (2021) A Convolutional Neural Network-Based Degradation Indicator Construction and Health Prognosis Using Bidirectional Long Short-Term Memory Network for Rolling Bearings. Advances in Engineering Information 48:101247. https://doi.org/10.1016/j.aei.2021.101247.
Yang Y, Zhao X, Zhao L (2022) Research on Asymmetrical Edge Tool Wear Prediction in Milling TC4 Titanium Alloy Using Deep Learning. Measurement 203:111814. https://doi.org/10.1016/j.measurement.2022.111814.
Zhou C, Chen C, Jin J (2021) Research on Tool Wear Monitoring Based on GRU-CNN. 2021 IEEE 6th International Conference on Intelligent Computing and Signal Processing (ICSP), April 09 - April 11, 2021, Xi'an, China: 729-733. https://doi.org/10.1109/ICSP51882.2021.9408717.
Kong D, Chen Y, Li N, Tan S (2017) Tool Wear Monitoring Based on Kernel Principal Component Analysis and Support Vector Regression. International Journal of Advanced Manufacturing Technology 89:175-190.
Chinomona B, Chung C, Chang L, Su W, Tsai M (2020) Long Short-Term Memory Approach to Estimate Battery Remaining Useful Life Using Partial Data. IEEE Access 8:165419-165431.
Cortez B, Carrera B, Kim YJ, Jung JY (2018) An Architecture for Emergency Event Prediction Using LSTM Recurrent Neural Networks. Expert Systems with Applications 97:315-324. https://doi.org/10.1016/j.eswa.2017.12.037.
Luo XJ, Oyedele LO (2021) Forecasting Building Energy Consumption: Adaptive Long-Short Term Memory Neural Networks Driven by Genetic Algorithm. Advances in Engineering Information 50:101357. https://doi.org/10.1016/j.aei.2021.101357.
Zhang J, Wang P, Yan R, Gao RX (2018) Long Short-Term Memory for Machine Remaining Life Prediction. Journal of Manufacturing Systems:78-86. https://doi.org/10.1016/j.jmsy.2018.05.011.
Kurek J, Wieczorek G, Swiderski B, Kruk M, Jegorowa A, Gorski J (2017) Automatic Identification of Drill Condition During Drilling Process in Standard Laminated Chipboard with the Use of Long Short-Term Memory (LSTM). In Eighth International Conference on Graphic and Image Processing (ICGIP 2016), 102251V. SPIE. https://doi.org/10.1117/12.2266254.
König F, Marheineke J, Jacobs G, Sous C, Zuo MJ, Tian Z (2021) Data-Driven Wear Monitoring for Sliding Bearings Using Acoustic Emission Signals and Long Short-Term Memory Neural Networks. Wear 476:203616. https://doi.org/10.1016/j.wear.2021.203616.
Zhao R, Wang J, Yan R, Mao K (2016) Machine Health Monitoring with LSTM Networks. 2016 Tenth International Conference on Sensing Technology (ICST), November 11 - November 13, 2016, Nanjing, China. IEEE.
Lu F, Zhou G, Zhang C, Liu Y, Chang F, Xiao Z (2023) Energy-Efficient Multi-Pass Cutting Parameters Optimisation for Aviation Parts in Flank Milling with Deep Reinforcement Learning. Robotics and Computer-Integrated Manufacturing 81:102488. https://doi.org/10.1016/j.rcim.2022.102488.
Lakshmanan S, Pradeep Kumar M, Dhananchezian M (2023) Optimization of Turning Parameter on Surface Roughness, Cutting Force and Temperature Through TOPSIS. Materials Today: Proceedings 72(4):2231-2237. https://doi.org/10.1016/j.matpr.2022.09.209.