本論文旨在研究線切割放電加工SKD11模具鋼時，電火花品質與表面粗糙度間的關係，探討線切割放電加工時正常放電、電弧放電與短路放電，於加工的品質特性如工件寬度、加工時間與表面粗糙度的影響，並利用正常放電次數、電弧放電次數和短路放電次數三種參數，以超參數優化之機器學習模型預測工件之表面粗糙度。
本研究係使用超參數優化之機器學習模型來預測線切割放電加工SKD11模具鋼之表面粗糙度，所使用的模型包括ANN、SVR和XGBoost，其中使用了網格搜索法、貝葉斯優化法和TPE等三種超參數優化法對模型的超參數進行優化，並比較了優化前與優化後的模型，結果顯示表現最佳的Validation MAPE與測試組 MAPE為TPE優化ANN模型，其Validation MAPE為1.86%，而MAPE為1.472%，在新增10組測試組的預測中，結果顯示表現最佳的MAPE為貝葉斯優化與TPE優化ANN模型，其MAPE分別為0.95%與1.01%，綜上所述，TPE優化ANN模型為本研究中之最佳模型。

In this study, the relationship between electrical discharge spark quality and surface roughness of SKD11 die steel in wire electrical discharge machining (WEDM) was investigated. The effects of normal sparks, arc sparks, and short sparks on quality characteristics such as the workpiece width, machining time, and surface roughness were examined. Using machine learning models optimized with hyperparameter tuning, the surface roughness of a workpiece by employing three input parameters, namely normal spark counts, arc spark counts, and short spark counts was predicted. The multiple hyperparameter optimization techniques were used, including artificial neural networks (ANNs), support vector regression, and extreme gradient boosting, to predict the surface roughness of SKD11 die steel in WEDM. Three hyperparameter optimization methods, namely grid search, Bayesian optimization, and tree-structured Parzen estimation (TPE) were used to optimize the hyperparameters of the models. The models were compared before and after optimization. The results indicated that among all models, the TPE-optimized ANN model exhibited the highest performance in terms of mean absolute percentage error (MAPE) and validation MAPE, with the respective values of 1.472% and 1.86%. Prediction of an additional 10 test groups revealed that, among all models, the Bayesian-optimized ANN model and TPE-optimized ANN model exhibited the highest performance, with a MAPE of 0.95% and 1.01%, respectively. In conclusion, the TPE-optimized ANN model is the optimal model in this study.

參考文獻
[1] R. S. Peres, X. Jia, J. Lee, K. Sun, A. W. Colombo, and J. Barata, “Industrial artificial intelligence in industry 4.0-systematic review, challenges and outlook”, IEEE Access, Vol. 8, pp. 220121-220139, 2020.
[2] B. Nikolic, J. Ignjatic, N. Suzic, B. Stevanov, and A. Rikalovic, “Predictive manufacturing systems in industry 4.0: trends, benefits and challenges”, Annals of DAAAM & Proceedings, Vol. 28, pp.0796-0202, 2017.
[3] K. Ho & S. Newman, “State of the art electrical discharge machining (EDM) ”, International Journal of Machine Tools and Manufacture, Vol. 43, no. 13, pp. 1287-1300, 2003.
[4] N. M. Abbas, D. G. Solomon, & M. F. Bahari, “A review on current research trends in electrical discharge machining (EDM) ”, International Journal of machine tools and Manufacture, Vol. 47, no. 7-8, pp. 1214-1228, 2007.
[5] J. E. A. Qudeiri, A. Zaiout, A. H. I. Mourad, M. H. Abidi, & A. Elkaseer, “Principles and characteristics of different EDM processes in machining tool and die steels”, Applied sciences, Vol. 10, no. 6, pp. 2082-2128, 2020.
[6] S. Singh, S. Maheshwari, & P. Pandey, “Some investigations into the electric discharge machining of hardened tool steel using different electrode materials”, Journal of materials processing technology, Vol. 149, no. 1-3, pp. 272-277, 2004.
[7] C. C. Chen et al., “A novel efficient big data processing scheme for feature extraction in electrical discharge machining”, IEEE Robotics and Automation Letters, Vol. 4, no. 2, pp. 910-917, 2019.
[8] 翁逸驊，「深度學習模型於工業4.0之機台虛擬量測應用」，國立中央大學，碩士論文，2019。
[9] Y. Liao & J. Woo, “The effects of machining settings on the behavior of pulse trains in the WEDM process”, Journal of Materials Processing Technology, Vol. 71, no. 3, pp. 433-439, 1997.
[10] J. Kao & Y. Tarng, “A neutral-network approach for the on-line monitoring of the electrical discharge machining process”, Journal of Materials Processing Technology, Vol. 69, no. 1-3, pp. 112-119, 1997.
[11] Y. Liao, M. Yan, & C. Chang, “A neural network approach for the on-line estimation of workpiece height in WEDM”, Journal of Materials Processing Technology, Vol. 121, no. 2-3, pp. 252-258, 2002.
[12] K. Wang, H. L. Gelgele, Y. Wang, Q. Yuan, & M. Fang, “A hybrid intelligent method for modelling the EDM process”, International Journal of Machine Tools and Manufacture, Vol. 43, no. 10, pp. 995-999, 2003.
[13] D. K. Panda & R. K. Bhoi, “Artificial neural network prediction of material removal rate in electro discharge machining”, Materials and Manufacturing Processes, Vol. 20, no. 4, pp. 645-672, 2005.
[14] U. Esme, A. Sagbas, & F. Kahraman, “Prediction of surface roughness in wire electrical discharge machining using design of experiments and neural networks”, Iranian Journal of Science & Technology, Vol. 33, No. B3, pp. 231-240 2009.
[15] A. Kumar, V. Kumar, & J. Kumar, “Prediction of surface roughness in wire electric discharge machining (WEDM) process based on response surface methodology”, International Journal of Engineering and Technology, Vol. 2, no. 4, pp. 708-719, 2012.
[16] G. Zhang, Z. Zhang, J. Guo, W. Ming, M. Li, & Y. Huang, “Modeling and optimization of medium-speed WEDM process parameters for machining SKD11”, Materials and Manufacturing Processes, Vol. 28, no. 10, pp. 1124-1132, 2013.
[17] V. Singh & S. Pradhan, “Optimization of WEDM parameters using Taguchi technique and response surface methodology in machining of AISI D2 steel”, Procedia Engineering, Vol. 97, pp. 1597-1608, 2014.
[18] A. Conde, J. Sánchez, S. Plaza, M. Olivenza, & J. Ramos, “An industrial system for estimation of workpiece height in WEDM”, Procedia engineering, Vol. 132, pp. 647-654, 2015.
[19] B. B. Nayak & S. S. Mahapatra, “Optimization of WEDM process parameters using deep cryo-treated Inconel 718 as work material”, Engineering Science and Technology, an International Journal, Vol. 19, no. 1, pp. 161-170, 2016.
[20] H. Gurupavan, T. Devegowda, H. Ravindra, & G. Ugrasen, “Estimation of machining performances in WEDM of aluminium based metal matrix composite material using ANN”, Materials Today: Proceedings, Vol. 4, no. 9, pp. 10035-10038, 2017.
[21] T. Singh, P. Kumar, & J. P. Misra, “Surface roughness prediction modelling for wedm of aa6063 using support vector machine technique”, Materials Science Forum, Vol. 969: Trans Tech Publ, pp. 607-612, 2019.
[22] Y. Yusoff, A. M. Zain, A. Amrin, S. Sharif, H. Haron, & R. Sallehuddin, “Orthogonal based ANN and multiGA for optimization on WEDM of Ti–48Al intermetallic alloys”, Artificial Intelligence Review, Vol. 52, pp. 671-706, 2019.
[23] M. R. Phate & S. B. Toney, “Modeling and prediction of WEDM performance parameters for Al/SiCp MMC using dimensional analysis and artificial neural network”, Engineering Science and Technology, an International Journal, Vol. 22, no. 2, pp. 468-476, 2019.
[24] M. Ulas, O. Aydur, T. Gurgenc, & C. Ozel, “Surface roughness prediction of machined aluminum alloy with wire electrical discharge machining by different machine learning algorithms”, Journal of Materials Research and Technology, Vol. 9, no. 6, pp. 12512-12524, 2020.
[25] C. Naresh, P. Bose, & C. Rao, “Artificial neural networks and adaptive neuro-fuzzy models for predicting WEDM machining responses of Nitinol alloy: Comparative study”, SN Applied Sciences, Vol. 2, pp. 1-23, 2020.
[26] H. V. Ozkavak, M. M. Sofu, B. Duman, & S. Bacak, “Estimating surface roughness for different EDM processing parameters on Inconel 718 using GEP and ANN”, CIRP Journal of Manufacturing Science and Technology, Vol. 33, pp. 306-314, 2021.
[27] J. Binoj, N. Manikandan, P. Thejasree, K. Varaprasad, P. Sasikala, & M. Manideep, “Application of Predictive Models for Wire Electrical Discharge Machining of Nickel Alloy”, Recent Advances in Materials and Modern Manufacturing: Select Proceedings of ICAMMM : Springer, pp. 1003-1011, 2021.
[28] A. S. Verma & S. Singh, “Experimental investigation and prediction modelling of slicing speed and surface roughness during wafer slicing using WEDM”, Engineering Research Express, Vol. 4, no. 3, pp. 035028-035040, 2022.
[29] A. Chaudhary, S. Sharma, & A. Verma, “Optimization of WEDM process parameters for machining of heat treated ASSAB’88 tool steel using Response surface methodology (RSM) ”, Materials Today: Proceedings, Vol. 50, pp. 917-922, 2022.
[30] R. Liu, E. Liu, J. Yang, M. Li, & F. Wang, “Optimizing the hyper-parameters for SVM by combining eVolution strategies with a grid search”, Intelligent Control and Automation: International Conference on Intelligent Computing , 2006: Springer, pp. 712-721, ICIC 2006 Kunming, China, August 16-19, 2006.
[31] J. Bergstra, R. Bardenet, Y. Bengio, & B. Kégl, “Algorithms for hyper-parameter optimization”, Advances in neural information processing systems, Vol. 24, pp. 1-9, 2011.
[32] J. Bergstra & Y. Bengio, “Random search for hyper-parameter optimization”, Journal of machine learning research, Vol. 13, no. 2, 2012.
[33] J. Snoek, H. Larochelle, & R. P. Adams, “Practical bayesian optimization of machine learning algorithms”, Advances in neural information processing systems, Vol. 25, 2012.
[34] I. Syarif, A. Prugel Bennett, & G. Wills, “SVM parameter optimization using grid search and genetic algorithm to improve classification performance”, Telecommunication Computing Electronics and Control, Vol. 14, no. 4, pp. 1502-1509, 2016.
[35] J. Wang, J. Xu, & X. Wang, “Combination of hyperband and Bayesian optimization for hyperparameter optimization in deep learning”, arXiv preprint arXiv:1801.01596, 2018.
[36] M. Nishio et al., “Computer-aided diagnosis of lung nodule using gradient tree boosting and Bayesian optimization”, PloS one, Vol. 13, no. 4, pp. 0195875-0195888, 2018.
[37] P. Liashchynskyi & P. Liashchynskyi, “Grid search, random search, genetic algorithm: a big comparison for NAS”, arXiv preprint arXiv:1912.06059, 2019.
[38] T. Akiba, S. Sano, T. Yanase, T. Ohta, & M. Koyama, “Optuna: A next-generation hyperparameter optimization framework”, Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pp. 2623-2631, 2019.
[39] J. Wu, X. Y. Chen, H. Zhang, L. D. Xiong, H. Lei, & S. H. Deng, “Hyperparameter optimization for machine learning models based on Bayesian optimization”, Journal of Electronic Science and Technology, Vol. 17, no. 1, pp. 26-40, 2019.
[40] F. Ghanbari Adivi & M. Mosleh, “Text emotion detection in social networks using a novel ensemble classifier based on Parzen Tree Estimator (TPE)”, Neural Computing and Applications, Vol. 31, no. 12, pp. 8971-8983, 2019.
[41] C. L. Fan and J. R. Jiang, “Surface roughness prediction based on Markov chain and deep neural network for wire electrical discharge machining” IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE), IEEE, pp. 191-194, 2019
[42] H. P. Nguyen, J. Liu, & E. Zio, “A long-term prediction approach based on long short-term memory neural networks with automatic parameter optimization by Tree-structured Parzen Estimator and applied to time-series data of NPP steam generators”, Applied Soft Computing, Vol. 89, pp. 106116-106132, 2020.
[43] L. Yang & A. Shami, “On hyperparameter optimization of machine learning algorithms: Theory and practice”, Neurocomputing, Vol. 415, pp. 295-316, 2020.
[44] P. T. dos Santos et al., “Multiclass Legal Judgment Outcome Prediction for Consumer Lawsuits Using XGBoost and TPE”, 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), IEEE, pp. 881-886, 2020.
[45] H. Cho, Y. Kim, E. Lee, D. Choi, Y. Lee, & W. Rhee, “Basic enhancement strategies when using bayesian optimization for hyperparameter tuning of deep neural networks”, IEEE access, Vol. 8, pp. 52588-52608, 2020.
[46] A. H. Victoria & G. Maragatham, “Automatic tuning of hyperparameters using Bayesian optimization”, EVolving Systems, Vol. 12, pp. 217-223, 2021.
[47] J. R. Jiang and C. T. Yen, “Product quality prediction for wire electrical discharge machining with Markov transition fields and convolutional long short-term memory neural networks” Applied Sciences, vol. 11, no. 13, p. 5922, 2021.
[48] S. Sharma, S. Sharma, & A. Athaiya, “Activation functions in neural networks”, Towards Data Sci, Vol. 6, no. 12, pp. 310-316, 2017.
[49] C. Nwankpa, W. Ijomah, A. Gachagan, & S. Marshall, “Activation functions: Comparison of trends in practice and research for deep learning”, arXiv preprint arXiv:1811.03378, 2018.
[50] G. Klambauer, T. Unterthiner, A. Mayr, & S. Hochreiter, “Self-normalizing neural networks”, Advances in neural information processing systems, Vol. 30, 2017.
[51] 吳俊諺，「應用SVR於預測性維修中衰退狀態資料之預測」，國立臺灣科技大學，碩士論文， 2017。
[52] H. Drucker, C. J. Burges, L. Kaufman, A. Smola, & V. Vapnik, “Support vector regression machines”, Advances in neural information processing systems, Vol. 9, 1996.
[53] R. Guo, Z. Zhao, T. Wang, G. Liu, J. Zhao, & D. Gao, “Degradation state recognition of piston pump based on ICEEMDAN and XGBoost”, Applied Sciences, Vol. 10, no. 18, pp. 6593-6610, 2020.
[54] 陳伯杰，「比較隨機森林和XGBoost的預測強韌性」，淡江大學，碩士論文，2022。
[55] 劉邦彥，「類自主機器學習與捲積加速器之研究與合成」，國立成功大學， 碩士論文，2021。
[56] E. Brochu, V. M. Cora, & N. De Freitas, “A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning”, arXiv preprint arXiv:1012.2599, 2010.
[57] J. Li, L. Jing, & M. Chen, “An FEM study on residual stresses induced by high-speed end-milling of hardened steel SKD11”, Journal of Materials Processing Technology, Vol. 209, no. 9, pp. 4515-4520, 2009.
[58] S. W. Choi, Y. S. Kim, Y. J. Yum, & S. Y. Yang, “A study on strengthening mechanical properties of a punch mold for cutting by using an HWS powder material and a DED semi-AM method of metal 3D printing”, Journal of Manufacturing and Materials Processing, Vol. 4, no. 4, pp. 98-113, 2020.
[59] A. Mahmudah, G. Kiswanto, & D. Priadi, “Fabrication of punch and die of micro-blanking tool”, IOP Conference Series: Materials Science and Engineering, Vol. 215, no. 1: IOP Publishing, pp. 012040-012049, 2017.
[60] D. Singh & B. Singh, “Investigating the impact of data normalization on classification performance”, Applied Soft Computing, Vol. 97, pp. 105524-105546, 2020.
[61] D. P. Kingma & J. Ba, “Adam: A method for stochastic optimization”, arXiv preprint arXiv:1412.6980, 2014.
[62] K. Ito & R. Nakano, “Optimizing support vector regression hyperparameters based on cross-validation”, Proceedings of the International Joint Conference on Neural Networks, Vol. 3: IEEE, pp. 2077-2082, 2003.
[63] S. Putatunda & K. Rama, “A comparative analysis of hyperopt as against other approaches for hyper-parameter optimization of XGBoost”, Proceedings of the 2018 international conference on signal processing and machine learning, pp. 6-10, 2018.