隨著工業4.0的發展，針對產品的品質全檢顯得越來越重要，其中航太、汽機車、大小型機械所使用到的金屬扣件也屬於其中一環。傳統金屬扣件的硬度檢測主要採取隨機抽樣檢測法，對樣本進行破壞性檢測，然而此種檢測方式有著效率不足、成本過高、生產線不靈活的缺點，不足以達到工業4.0所重視的品質全檢，也可能使應用上產生不可預期的安全問題。本文以此為改善目標，提出一套可應用於不同鋼材的金屬扣件進行全檢分類的非破壞性檢測系統，應用渦電流檢測技術將線圈探頭量測到的輸出值，透過主成份分析計算出最佳頻率點，利用最佳頻率點的阻抗實部值與阻抗虛部值作為硬度分類依據，投入隨機森林演算法進行機器學習的訓練，將其整合到系統中立即線上學習並進行實時智慧檢測分類，最後利用不同鋼材的金屬扣件進行實測驗證。本文結果顯示此系統能有效提升高速產線上的適用性，且隨機森林演算法在快速的模型訓練後，能達到高分辨率的分類。

With the development of Industry 4.0, full-inspection of on-line products has become more and more important. Metal fasteners used in aerospace, automobile, motorcycle and machinery. Traditional hardness testing is mainly used for random sampling inspection of metal fasteners, which destroys the samples. This detection method has the disadvantages of insufficient efficiency, high cost and inflexible production line, so it is not sufficient to achieve full-inspection. It also may cause unexpected security issues in the application. Therefore, the purpose of this thesis is to improve the above-mentioned problems. It is proposed that a nondestructive testing system for various metal fasteners can be applied to different steels. The system will measure the output value of the detection probe with eddy currents and calculate the best frequency point with Principal Components Analysis(PCA). For the hardness classification, we will use the resistance and reactance at the best frequency point and implement machine learning with Random Forest Algorithm. Finally, integrated into a system for real-time online machine learning and immediately detect classification. At last, this thesis test and verify through metal fasteners of different steels. The results show that the system can effectively improve the applicability of the high-speed production line, and achieve a high resolution of classification with a quick Random Forest model training.

[1] T. H. Hejazi and S. Kahrobaee, “A predictive model for characterizing hardness of D2 tool steel by eddy current method: A statistical optimization approach”, Research in Nondestructive Evaluation, vol. 29, no. 4, pp. 237-254, 2018.
[2] N. Korde and T. Kundu, “Material hardness and ageing measurement using guided ultrasonic waves”, Ultrasonics, vol. 53, no. 2, pp. 506-510, 2013.
[3] F. A. Franco, M. F. D. Campos and L. R. Padovese, “Relation Between Magnetic Barkhausen Noise and Hardness for Jominy Quench Tests in SAE 4140 and 6150 Steels”, Journal of Nondestructive Evaluation, vol. 32, no. 1, pp. 93-103, 2013.
[4] C. He, Y. Meng, X. Liu, X. Wang and B. Wu, “Characterisation of case depth in induction-hardened medium carbon steels based on magnetic minor hysteresis loop measurement technique”, Philosophical Magazine, vol. 97, no. 31, pp. 1-16, 2017.
[5] J. N. Mohapatra, A. K. Akela, S. K. Dabbiru and M. Sambandam, “Magnetic hysteresis loop technique as a NDE tool for the evaluation of microstructure and mechanical properties of 2.25Cr–1Mo steel”, Journal of Nondestructive Evaluation, vol. 37, no. 2, pp. 36, 2018.
[6] T. Matsumoto, T. Uchimoto, T. Takagi, G. Vertesy, F. Kojima, F. Kobayashi and H. Nakamoto, “Evaluation of chill structure in ductile cast iron by incremental permeability method”, International Journal of Applied Electromagnetics and Mechanics, vol. 52, no. 3-4, pp. 1599-1605, 2016.
[7] C. C. Tai, J. H. Rose and J. C. Moulder, “Thickness And Conductivity of Metallic Layers From Pulsed Eddy Current Measurements”, Review of Scientific Instruments. vol. 67, no. 11, pp. 3965-3972, 1996.
[8] 劉尹雄，「脈衝式渦電流檢測系統之設計與應用」，國立成功大學電機工程學系碩士論文，1999。
[9] C. C. Tai, “Characterization of coatings on magnetic metal using the swept frequency eddy current method”, Review of Scientific Instruments, vol. 71, no. 8 pp. 3161-3167, 2000.
[10] C. C. Tai and H. C. Yang, “The interaction of eddy current with metal hidden flaws for various probes”, Journal of Technology, vol. 17, no. 4, pp. 525-533, 2002.
[11] C. C. Tai, H. C. Yang and Y. H. Lin, “Modeling the surface condition of ferromagnetic metal by the swept-frequency eddy current method”, IEEE Transactions on Magnetics, vol. 38, no. 1, pp. 205-210, 2002.
[12] H. C. Yang and C. C. Tai, “Pulsed eddy-current measurement of a conducting coating on a magnetic metal plate”, Measurement Science and Technology, vol. 13, no. 1, pp. 1259–1265, 2002.
[13] C. C. Tai and S. F. Wang, “Time-Domain and Frequency-Domain Eddy Current Simulations by the Finite Element Method”, Key Engineering Materials, vol. 270-273, pp. 585-592, 2004.
[14] Y. L. Pan and C. C. Tai, “Thickness and Conductivity Analysis of Molybdenum Thin Film in CIGS Solar Cells Using Resonant Electromagnetic Testing Method”, Magnetics, IEEE Transactions on, vol. 48, no. 2, pp. 347-350, 2012.
[15] 陳林湋，「低頻渦電流金屬厚度檢測系統研製」，國立成功大學電機工程學系碩士論文，2012。
[16] 李柏毅，「非接觸式微米級金屬薄膜檢測系統研製及田口法最佳感測線圈設計」，國立成功大學電機工程學系碩士論文，2017。
[17] 林茂盛，「架構於FPGA之掃頻式阻抗分析儀暨金屬薄膜厚度估測應用」，國立成功大學電機工程學系碩士論文，2018。
[18] 賴行健，「倒傳遞神經網路及主成份分析應用於金屬扣件硬度篩選檢測:系統設計與評估」，國立成功大學電機工程學系碩士論文，2019。
[19] 李耘多，「基於K-近鄰分類法及梯度提升決策樹模型之印刷電路板銅膜厚度渦電流量測」，國立成功大學電機工程學系碩士論文，2020。
[20] 莊宗霖，「隨機森林法應用於渦電流金屬扣件硬度分類」，國立成功大學電機工程學系碩士論文，2020。
[21] S.Konoplyuk, “Estimation of pearlite fraction in ductile cast irons by eddy current method”, NDT & E International, vol. 43, no. 4, pp. 360-364, 2010.
[22] D. Diehl, C. Köhler, E. L. Schneider, and T. G. R. Clarke, “Eddy Current at High Temperatures for in-Situ Control of Heat Treatment Precipitation in Hardening Aluminum Alloys”, IEEE SENSORS JOURNAL, vol. 20, no. 23, pp. 14514-14520, 2020.
[23] S. Kahrobaee, and M. Kashefi, “Hardness profile plotting using multi-frequency multi-output electromagnetic sensor”, NDT & E International, vol. 44, no. 4, pp. 335-338, 2011.
[24] S. Kahrobaee, and E. Z. Karimi, “Characterisation of work-hardening in Hadfield steel using non-destructive eddy current method”, Nondestructive Testing and Evaluation, vol. 34, no. 2, pp. 178-192, 2019.
[25] X. J. Hao, W. Yin, M. Strangwood, A. J. Peyton, P. F. Morris, and C. L. Davisa, “Off-line measurement of decarburization of steels using a multifrequency electromagnetic sensor”, Scripta Materialia, vol. 58, no. 11, pp. 1033-1036, 2008.
[26] L. Janousek, A. Stubendekova, and M. Smetana, “Novel insight into swept frequency eddy-current non-destructive evaluation of material defects”, Measurement, vol. 116, pp. 246-250, 2018.
[27] L. K. Kogan, A. P. Nichipuruk and L. D. Gavrilova, “Effect of the carbon content on the magnetic and electric properties of thermally treated carbon steels and the possibilities of testing the quality of tempering of articles produced from them via the eddy-current method”, Russian Journal of Nondestructive Testing, vol. 42, no. 9, pp. 616-629, 2006.
[28] B. Lei, P. Yi, Y. Li and J. Xiang, “A Temperature Drift Compensation Method for Pulsed Eddy Current Technology”, Sensors(Basel), vol. 18, no. 6, 2018.
[29] B. Lei, P. Yi, Y. Li and J. Xiang, “Noncontact Thickness Measurement of Metal Films Using Eddy-Current Sensors Immune to Distance Variation”, IEEE Transactions on Instrumentation and Measurement, vol. 64, no. 9, pp. 2557-2564, 2015.
[30] S. Konoplyuk, T. Abe, T. Uchimoto, T. Takagi and M. Kurosawa, “Characterization of ductile cast iron by eddy current method”, NDT & E International, vol. 38, no. 8, pp. 623-626, 2005.
[31] M. S. Amiri and M. Kashefi, “Application of eddy current nondestructive method for determination of surface carbon content in carburized steels”, NDT & E International, vol. 42, no. 7, pp. 618-621, 2009.
[32] S. Kahrobaee, M. Kashefi and A. S. Alam, “Magnetic NDT Technology for characterization of decarburizing depth”, Surface and Coatings Technology, vol. 205, no. 16, pp. 4083-4088, 2011.
[33] J. Fan, S. Chen, X. Luo, Y. Zhang and G. Y. Li, “A Machine Learning Approach for Hierarchical Localization Based on Multipath MIMO Fingerprints”, IEEE Communications Letters, vol. 23, no. 10, pp. 1765-1768, 2019.
[34] M. Min, C. Bai, J. Guo, F. Sun, C. Liu, F. Wang, H. Xu, S. Tang, B. Li, D. Di, L. Dong and J. Li, “Estimating Summertime Precipitation from Himawari-8 and Global Forecast System Based on Machine Learning”, IEEE Transactions on Geoscience and Remote Sensing, vol. 57, no. 5, pp. 2557-2570, 2019.
[35] N. Reamaroon, M. W. Sjoding, K. Lin, T. J. Iwashyna and K. Najarian, “Accounting for Label Uncertainty in Machine Learning for Detection of Acute Respiratory Distress Syndrome”, IEEE Journal of Biomedical and Health Informatics, vol. 23, no. 1, pp. 407-415, 2019.
[36] L. Breiman, J. H. Friedman, C. J. Stone, R. A. Olshen, “Classification and Regression Trees”, CA: Wadsworth & Brooks/Cole Advanced Books & Software, 1984.
[37] L. Breiman, “Random Forests”, Machine Learning, vol. 45, no.1, pp. 5-32, 2001.
[38] “Discrete Fourier Transform v3.1”, Xilinx Logicore IP, 2011.
[39] G. F. Zhao, J. Ying, L. Wu and Z. H. Feng, “Eddy current displacement sensor with ultrahigh resolution obtained through the noise suppression of excitation voltage”, Sensors and Actuators A: Physical, vol. 299, 2019.
[40] H. Wang and Z. Feng, “Ultrastable and highly sensitive eddy current displacement sensorusing self-temperature compensation”, Sensors and Actuators A: Physical, vol. 203, pp. 362-368, 2013.
[41] H. Wang, B. Ju, W. Li and Z. Feng, “Ultrastable eddy current displacement sensor working in harshtemperature environments with comprehensive self-temperature compensation”, Sensors and Actuators A: Physical, vol. 211, pp. 98-104, 2014.
[42] F. E. Grubbs, “Sample criteria for testing outlying observations”, Annals of Mathematical Statistics, vol. 21, no.1, pp. 27-58, 1950.
[43] "Standard practice for dealing with outlying observations", American Society for Testing and Materials(ASTM: E178-08), 2002.
[44] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Perrot and É. Duchesnay, “Scikit-learn: Machine Learning in Python”, Journal of Machine Learning Research, vol. 12, pp. 2825-2830, 2011.
[45] J. M. Shearer and M. A. Wolfe, “ALGLIB, a simple symbol-manipulation package”, Communications of the ACM, vol. 28, no.8 ,pp. 820-825, 1985.
[46] D. Mercier, J. Lesage, X. Decoopman and D.Chicot, “Eddy currents and hardness testing for evaluation of steel decarburizing”, NDT & E International, Vol. 39, pp. 652-660, 2006.
[47] S. Ghanei, M. Kashefi and M. Mazinani, “Eddy current nondestructive evaluation of dual phase steel”, Materials and Design, vol. 50, pp. 491-496, 2013.