臺灣博碩士論文加值系統

刀具磨耗是影響成品品質的重要依據，刀具磨耗會隨著車削加工持續增加，進而影響加工品質、生產效率和生產成本，故監控刀具磨耗是機械車削加工中重要技術，本研究以適應性類神經模糊推論系統開發S50C刀具磨耗檢測之預測系統為目標，開發對精加工之高轉速低切削深度之刀具磨耗預測系統，經頻譜分析得出主要加工振動加速度頻率，透過加工振動加速度變化，量化刀具磨耗狀態，並解析製程參數對磨耗之影響，找出刀具磨耗臨界值，透過訓練適應性類神經模糊推論系統，預測振動加速度均方根值、刀面磨耗面積與刀腹平均磨耗深度，運用LabVIEW軟體開發具人機介面之即時檢測刀具磨耗系統。
研究結果顯示，加工刀具磨耗主要響應頻率段為2900~3100 Hz，預測系統透過主要響應頻率段進行訓練，得到於模型預測振動臨界值RMSE為0.10479，於預測刀面磨耗面積RMSE為0.14104，於預測平均刀腹磨耗深度RMSE為0.08481，結合刀具磨耗燈號警示與警報功能，成功開發即時檢測刀具磨耗系統，系統可即時檢測判斷磨耗狀態與提供換刀時機提醒，經預測模型準確率達89%以上。具可配合製程參數變化，自動修正判斷依據，即時預測刀具磨耗。

Tool wear is an important factor that affects the quality of finished products. As machining operations continue, tool wear increases, thereby impacting processing quality, production efficiency, and production costs. Therefore, monitoring tool wear is a critical technology in mechanical turning processes.
This study aims to develop a predictive system for detecting tool wear in S50C tools using an adaptive neural fuzzy inference system. The goal is to develop a predictive system for high-speed and low-depth-of-cut precision machining. The main machining vibration acceleration frequencies are determined through spectrum analysis. By quantifying the changes in machining vibration acceleration, the tool wear condition is assessed, and the influence of process parameters on wear is analyzed. The critical threshold for tool wear is identified. An adaptive neural fuzzy inference system is trained to predict the root mean square value of vibration acceleration, tool face wear area, and average flank wear depth. The LabVIEW software is used to develop a human-machine interface for real-time tool wear detection.
 
The research findings indicate that the main response frequency range for tool wear during machining is 2900 to 3100 Hz. The predictive system, trained on the main response frequency range, achieves a root mean square error (RMSE) of 0.10479 for predicting vibration critical values, 0.14104 for predicting tool face wear area, and 0.08481 for predicting average flank wear depth. By incorporating tool wear signal warnings and alarms, a real-time tool wear detection system is successfully developed, enabling immediate assessment of wear condition and timely tool replacement reminders. The predictive model demonstrates an accuracy of over 89% and can adapt to changes in process parameters, automatically adjusting the assessment criteria for real-time tool wear prediction.

摘要 i
ABSTRACT ii
誌 謝 iv
目 錄 v
表 目 錄 vii
圖 目 錄 viii
第一章 緒論 1
1.1 研究背景 1
1.2 研究動機 2
1.3 研究目的 2
1.4 論文架構 3
第二章 文獻回顧 4
2.1 刀具磨耗監測概況及需求 4
2.2 振動分析技術 6
2.3 適應性類神經模糊推論系統 8
第三章 理論基礎介紹 12
3.1 田口品質工程法 12
3.2 適應性類神經模糊推論系統原理 18
第四章 研究方法 22
4.1 研究流程 22
4.2 刀具磨耗特性實驗 23
4.3 製程參數對磨耗影響實驗 32
4.4 實驗設備 35
4.5 實驗架構 41
第五章 刀具磨耗量化評估和結果分析 43
5.1 特徵擷取結果 43
5.2 刀具磨耗曲線 48
5.3 刀具磨耗臨界值 51
5.4 單目標優化結果分析 53
5.5 多目標優化結果分析 63
第六章 即時檢測刀具磨耗系統 66
6.1 適應性類神經模糊推論系統模型 66
6.2 即時檢測系統設計 82
第七章 結論與未來展望 86
7.1 結論 86
7.2 未來展望 87
參考資料 88

[1]Cantero, J.L., Díaz-Álvarez, J., Miguélez, M.H., Marín, N.C. (2013). Analysis of tool wear patterns in finishing turning of Inconel 718. Wear, 297(1-2), 885-894. https://doi.org/10.1016/j.wear.2012.11.004
[2]Debnath, S., Reddy, M.M., Yi, Q.S. (2016). Influence of cutting fluid conditions and cutting parameters on surface roughness and tool wear in turning process using Taguchi method. Measurement, 78, 111-119. https://doi.org/10.1016/j.measurement.2015.09.011
[3]Brinksmeier, E., Preuss, W., Riemer, O., Rentsch, R. (2017). Cutting forces, tool wear and surface finish in high speed diamond machining. Precision Engineering, 49, 293-304. https://doi.org/10.1016/j.precisioneng.2017.02.018
[4]Masmiati, N., Sarhan, A.A.D., Hassan, M.A.N., Hamdi, M. (2016). Optimization of cutting conditions for minimum residual stress, cutting force and surface roughness in end milling of S50C medium carbon steel. Measurement, 86, 253-265. https://doi.org/10.1016/j.measurement.2016.02.049
[5]Aslan, A. (2020). Optimization and analysis of process parameters for flank wear, cutting forces and vibration in turning of AISI 5140: A comprehensive study. Measurement, 163, 107959. https://doi.org/10.1016/j.measurement.2020.107959
[6]D’Addona, D.M., Ullah, A.M.M.S., Matarazzo, D. (2017). Tool-wear prediction and pattern-recognition using artificial neural network and DNA-based computing. Journal of Intelligent Manufacturing, 28(6), 1285-1301.
https://doi.org/10.1007/s10845-015-1155-0
[7]Mikołajczyk, T., Nowicki, K., Bustillo, A., Pimenov, Y.D. (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
[8]Li, Z., Liu, R., Wu, D. (2019). Data-driven smart manufacturing: Tool wear monitoring with audio signals and machine learning. Journal of Manufacturing Processes, 48, 66-76. https://doi.org/10.1016/j.jmapro.2019.10.020
[9]Bhuiyan, M.S.H., Choudhury, I.A., Dahari, M. (2014). Monitoring the tool wear, surface roughness and chip formation occurrences using multiple sensors in turning. Journal of Manufacturing Systems, 33(4), 476-487. https://doi.org/10.1016/j.jmsy.2014.04.005
[10]Elangovan, M., Sakthivel, N.R., Saravanamurugan, S., Nair, B.B., Sugumaran, V. (2015). Machine learning approach to the prediction of surface roughness using statistical features of vibration signal acquired in turning. Procedia Computer Science, 50, 282-288. https://doi.org/10.1016/j.procs.2015.04.047
[11]Arslan, H., Osman Er, A., Orhan, S., Aslan, E. (2016). Tool condition monitoring in turning using statistical parameters of vibration signal. The International Journal of Acoustics and Vibration, 21(4) 371-378. https://doi.org/10.20855/ijav.2016.21.4432
[12]González-Laguna, A., Barreiro, J., Fernández-Abia, A., Alegre, E., González-Castro, V. (2015). Design of a TCM system based on vibration signal for metal turning processes. Procedia Engineering, 132, 405-412. https://doi.org/10.1016/j.proeng.2015.12.512
[13]Liu, M.-K., Tseng, Y.-H., Tran, M.-Q. (2019). Tool wear monitoring and prediction based on sound signal. The International Journal of Advanced Manufacturing Technology, 103(9-12), 3361-3373. https://doi.org/10.1007/s00170-019-03686-2
[14]Panda, A., Sahoo, A.K., Panigrahi, I., Rout, A.K. (2020). Prediction models for on-line cutting tool and machined surface condition monitoring during hard turning considering vibration signal. Mechanics & Industry, 21(5), 520. https://doi.org/10.1051/meca/2020067
[15]Seemuang, N., McLeay, T., Slatter, T. (2016). Using spindle noise to monitor tool wear in a turning process. The International Journal of Advanced Manufacturing Technology, 86(9-12), 2781-2790. https://doi.org/10.1007/s00170-015-8303-8
[16]Stavropoulos, P., Papacharalampopoulos, A., Souflas, T. (2020). Indirect online tool wear monitoring and model-based identification of process-related signal. Advances in Mechanical Engineering, 12(5), 1-12. https://doi.org/10.1177/1687814020919209
[17]Sredanovic, B., Cica, D. (2015). Comparative study of ANN and ANFIS prediction models for turning process in different cooling and lubricating conditions. SAE International Journal of Materials and Manufacturing, 8(2), 586-591. https://www.jstor.org/stable/10.2307/26268749
[18]Sen, B., Mandal, U.K., Mondal, S.P. (2017). Advancement of an intelligent system based on ANFIS for predicting machining performance parameters of Inconel 690 – A perspective of metaheuristic approach. Measurement, 109, 9-17. https://doi.org/10.1016/j.measurement.2017.05.050
[19]Masoudi, S., Sima, M., Tolouei-Rad, M. (2018). Comparative study of ANN and ANFIS models for predicting temperature in machining. Journal of Engineering Science and Technology, 13(1), 211-225. https://www.researchgate.net/publication/322331410
[20]Naresh, C., Bose, P.S.C., Rao, C. S. P. (2020). Artificial neural networks and adaptive neuro-fuzzy models for predicting WEDM machining responses of Nitinol alloy: comparative study. SN Applied Sciences, 2(2) 314. https://doi.org/10.1007/s42452-020-2083-y
[21]Naresh, C., Bose, P.S.C., Suryaprakash Rao, C.S., Selvaraj, N. (2021). Prediction of cutting force of AISI 304 stainless steel during laser-assisted turning process using ANFIS. Materials Today: Proceedings, 38, 2366-2371. https://doi.org/10.1016/j.matpr.2020.07.074
[22]Bayram, D., Şeker, S. (2015). Anfis model for vibration signals based on aging process in electric motors. Soft Computing, 19(4), 1107-1114. https://doi.org/10.1007/s00500-014-1326-5
[23]Jain, V., Raj, T. (2017). Tool life management of unmanned production system based on surface roughness by ANFIS. International Journal of System Assurance Engineering and Management, 8(2), 458-467. https://doi.org/10.1007/s13198-016-0450-2
[24]Guvenc, M.A., Bilgic, H.H., Cakir, M., Mistikoglu, S. (2022). The prediction of surface roughness and tool vibration by using metaheuristic-based ANFIS during dry turning of Al alloy (AA6013). Journal of the Brazilian Society of Mechanical Sciences and Engineering, 44(10) 474. https://doi.org/10.1007/s40430-022-03798-z
[25]Jang, J.-S. (1993). ANFIS: adaptive-network-based fuzzy inference system. IEEE transactions on systems, man, and cybernetics, 23(3), 665-685.
[26]臥式車削中心TS-100系列，取自：程泰機械股份有限公司網頁： https://www.goodwaycnc.com/，線上檢索日期：2023 年 5 月 27 日
[27]外徑車削刀具，取自：Sandvik Coromant 公司網頁： https://www.sandvik.coromant.com/，線上檢索日期：2023 年 5 月 27 日
[28]高頻工業ICP加速度計，取自：PCB Piezotronics 公司網頁： https://www.pcb.com/，線上檢索日期：2023 年 5 月 27 日
[29]USB-443X規格表，取自：National Instruments 公司網頁： https://ni.com/，線上檢索日期：2023 年 5 月 27 日
[30]keyence vk-x110 規格表，取自：KEYENCE 公司網頁： https://www.keyence.com.tw/，線上檢索日期：2023 年 5 月 27 日