刀具磨耗是現代製造業中一個重要的議題。為了有效管理和監測刀具磨耗，非直接量測刀具磨耗的方法在過去幾十年來不斷地被研究，原因是直接量測方法須將刀具取下，必須中斷工作或工作完成後才能進行，而非直接量測可在工作中透過各式感測訊號的收集與分析達到磨耗評估的目標，但缺點是不一定準確，而訊號來源是否能反應出實際刀具磨耗狀況是重要考量因素，故訊號收集和特徵提取成為關鍵步驟之一。本研究聚焦於利用主軸電流訊號和加速規振動訊號來分析刀具磨耗狀態。主軸電流訊號能夠反映刀具與工件的切削力，而加速規振動訊號則能檢測刀具磨耗引起的振動變化。兩種訊號分別計算了平均值、標準差、方差、偏度和峰度等15種特徵，在特徵提取方面，我們採用了皮爾森積動差相關係數作為一種常用的方法。這種相關係數可以評估主軸電流訊號和加速規振動訊號與刀具磨耗之間的相關程度，從而選擇最具信息量的特徵。通過這種方式，我們能夠確定哪些訊號特徵能夠最準確地反映刀具磨耗程度。綜上所述，本研究旨在探討刀具磨耗對訊號收集和特徵提取的影響，並應用皮爾森積動差相關係數來選擇最佳特徵。結果顯示，當切削深度淺時，加速規振動訊號與刀具磨耗有較高的關聯性；然而，當切削深度加深時，主軸電流訊號與刀具磨耗的相關性較為突出。透過深入研究刀具磨耗的關鍵要素，我們可以提高刀具管理的準確性，並實現更有效的生產監測和預測。這將有助於提升生產效率、降低成本，並確保產品質量的穩定性。

This research focuses on the effects of spindle current signals and accelerometer vibration signals to evaluate tool wear. The spindle current signal can reflect the cutting force between the tool and the workpiece, while the accelerometer vibration signal can detect the vibration change caused by tool wear. Fifteen features, including mean, standard deviation, variance, skewness, and kurtosis, were calculated for each signal. Pearson product-moment correlation coefficient was employed as a commonly used method for feature extraction. This correlation coefficient assesses the degree of correlation between the spindle current signal, accelerometer vibration signal, and the tool wear, enabling the selection of the most informative features. Using this approach, the highly correlated signal features can be determined. The results showed that when the cutting depth was shallow, there was a higher correlation between the accelerometer vibration signal and tool wear. However, as the cutting depth increased, the correlation between the spindle current signal and tool wear became more prominent. By delving into the key factors of tool wear, we can enhance the accuracy of tool management and achieve more effective production monitoring and prediction. This will contribute to improving production efficiency, reducing costs, and ensuring the stability of product quality.

[1] Tool life testing in milling–Part 2：End milling. ISO 8688-2, 1989.
[2] Sun, H., Liu, Y., Pan, J., Zhang, J., Ji, W. (2020) Enhancing Cutting Tool Sustainability Based on Remaining Useful Life Prediction. Journal of Cleaner Production, Volume 244, 118794.
[3] Abubakr, M., Hassan, M. A., Krolczyk, G. M., Khanna, N., Hegab, H. (2021) Sensors Selection for Tool Failure Detection During Machining Processes: A Simple Accurate Classification Model. CIRP Journal of Manufacturing Science and Technology, Volume 32, Pages: 108-119.
[4] Díaz-Saldaña, G., Osornio-Ríos, R.A., Zamudio-Ramírez, I., Cruz-Albarrán, I.A., Trejo-Hernández, M., Antonino-Daviu, J.A. (2023) Methodology for Tool Wear Detection in CNC Machines Based on Fusion Flux Current of Motor and Image Workpieces. Machines, Volume 11, Issue 4, 480.
[5] Wei, X., Liu, X., Yue, C., Wang, L., Liang, S. Y., Qin, Y. (2022) Tool Wear State Recognition Based on Feature Selection Method with Whitening Variational Mode Decomposition. Robotics and Computer-Integrated Manufacturing, Volume 77, 102344.
[6] Duan, J., Hu, C., Zhan, X., Zhou, H., Liao, G., Shi, T. (2023) Milling Tool Wear Prediction Research Based on Optimized PCANet Model. Journal of Mechanical Engineering, Volume 59, Issue 1, Pages: 278-285.
[7] Huang, Z., Zhu, J., Lei, J., Li, X., Tian, F. (2021) Tool Wear Monitoring with Vibration Signals Based on Short-Time Fourier Transform and Deep Convolutional Neural Network in Milling. Mathematical Problems in Engineering, Volume 2021, 9976939.
[8] Mohanraj, T., Shankar, S., Rajasekar, R., Sakthivel, N.R., Pramanik, A. (2020) Tool Condition Monitoring Techniques in Milling Process — A Review. Journal of Materials Research and Technology, Volume 9, Issue 1, Pages: 1032-1042.
[9] Ghosh, N., Ravi, Y.B., Patra, A., Mukhopadhyay, S., Paul, S., Mohanty, A.R., Chattopadhyay, A.B. (2007) Estimation of Tool Wear During CNC Milling Using Neural Network-based Sensor Fusion. Mechanical Systems and Signal Processing, Volume 21, Issue 1, Pages: 466-479.
[10] Yuan, J., Liu, L., Yang, Z., Zhang, Y. (2020) Tool Wear Condition Monitoring by Combining Variational Mode Decomposition and Ensemble Learning. Sensors, Volume 20, Issue 21, 6113.
[11] Zhou, B., Zhang, J., Fu, Y., Yu, D., Wang, J. (2021) Feature Extraction and Analysis Method of Spindle Vibration Signal for Tool Wear Monitoring. 2021 5th International Conference on Automation, Control and Robots, Pages: 184-189.
[12] Zhang, Q., Shao, X. (2021) Tool Wear Monitoring in Milling Based on Accelerometer Vibration Signals and Machine Learning Techniques. Measurement, Volume 176, 109272.
[13] Li, H., Wang, Y., Wang, L., Gao, X. (2021) Tool Wear Monitoring in Milling Based on Wavelet Packet Entropy of Accelerometer Vibration Signals. Mechanical Systems and Signal Processing, Volume 151, 107479.
[14] Zhang, Y., Sun, M., Wang, D., Wang, L., He, Z. (2017) Tool Wear Monitoring Based on Wavelet Packet Transform and Support Vector Machine Using Accelerometer in Milling. Measurement, Volume 98, Pages: 307-317.
[15] Li, C., Li, B., Wang, H., Shi, D., Gu, F., Ball, A.D. (2023) Tool Wear Monitoring in CNC Milling Process Based on Vibration Signals from an On-Rotor Sensing Method. Mechanisms and Machine Science, Volume 129.
[16] Kaya, B., Oysu, C., Ertunc, H.M., Ocak, H. (2012) A Support Vector Machine-based Online Tool Condition Monitoring for Milling Using Sensor Fusion and a Genetic Algorithm. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, Volume 226, Issue 11, Pages: 1808-1818.
[17] Uekita, M., Takaya, Y. (2017) Tool Condition Monitoring for Form Milling of Large Parts by Combining Spindle Motor Current and Acoustic Emission Signals. The International Journal of Advanced Manufacturing Technology, Volume 89, Pages: 65-75.
[18] Zhou, Y., Sun, W. (2020) Tool Wear Condition Monitoring in Milling Process Based on Current Sensors. IEEE Access, Volume 8, Pages: 95491-95502.
[19] Jamshidi, M., Chatelain, J-F., Rimpault, X., Balazinski, M.. (2022) Tool Condition Monitoring Using Machine Tool Spindle Electric Current and Multiscale Analysis while Milling Steel Alloy. Journal of Manufacturing and Materials Processing, Volume 6, Issue 5, 115.
[20] Chen, X., Tuysuz, O. (2021) Tool Life Prediction Using Machine Learning: A Comprehensive Review. Journal of Manufacturing Systems, Volume 59, Pages: 371-388.
[21] Karpat, Y., Liang, S. Y. (2021) A Comprehensive Review of Cutting Tool Wear Monitoring and Prediction Techniques. Journal of Manufacturing Systems, Volume 60, Pages: 377-398.
[22] Wang, J., Wang, P., Gao, R. X. (2013) Tool Life Prediction for Sustainable Manufacturing.
[23] Wang, P., Gao, R. X. (2016) Stochastic Tool Wear Prediction for Sustainable Manufacturing. Procedia CIRP, Volume 48, Pages: 236-241.
[24] Arslan, H., ER, A., Orhan, S., Aslan, E. (2016) Tool Condition Monitoring in Turning Using Statistical Parameters of Vibration Signal. International Journal of Acoustics and Vibrations, Volume 21, Issue 4, Pages: 371-378.
[25] Chuangwen, X., Hualing, C. (2009) Fractal Analysis of Vibration Signals for Monitoring the Condition of Milling Tool Wear. Proceedings of the Institution of Mechanical Engineers, Part J: Journal of Engineering Tribology, Volume 223, Issue 6, Pages: 909-918.
[26] Guyon, I., Elisseeff, A. (2003) An Introduction to Variable and Feature Selection. Journal of Machine Learning Research, Volume 3, Pages: 1157-1182.
[27] Hall, M. A. (1999) Correlation-Based Feature Selection for Machine Learning. Hamilton, Doctoral dissertation, The University of Waikato.
[28] Kohavi, R., John, G. H. (1997) Wrappers for Feature Subset Selection. Artificial Intelligence, Volume 97, Issue 1-2, Pages: 273-324.
[29] Liu, H., Setiono, R. (2002) Feature Selection: Theory and Practice. Handbook of Data Mining and Knowledge Discovery, Pages: 87-111.
[30] Zhang, Y., Yang, J. (2018) A Survey on Feature Extraction and Representation Techniques for Machine Learning-based Vibration Analysis of Rotating Machinery. Mechanical Systems and Signal Processing, Volume 107, Pages: 33-57.
[31] Pearson, K. (1895) Notes on Regression and Inheritance in the Case of Two Parents. Proceedings of the Royal Society of London, Volume 58, Pages: 240-242.
[32] Pearson, K. (1900) X. On the Criterion that a Given System of Deviations from the Probable in the Case of a Correlated System of Variables is Such that it Can be Reasonably Supposed to have Arisen from Random Sampling. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, Volume 50, Issue 302, Pages: 157-175.
[33] 東台精機股份有限公司. “東台精機立式加工機.” https://www.tongtai.com.tw/tw/product-detail.php?id=172
[34] 震虎精密科技股份有限公司. “震虎綜合型錄 General Catalogue.” https://www.speedtiger.com.tw/document/