進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-0208201913422500
論文名稱(中文) 基於支持向量回歸渦電流金屬薄膜厚度檢測系統設計與評估
論文名稱(英文) Design and Evaluation of An Eddy-Current Metal Foil Thickness Detecting System Based on Support Vector Regression Method
校院名稱 成功大學
系所名稱(中) 電機工程學系
系所名稱(英) Department of Electrical Engineering
學年度 107
學期 2
出版年 108
研究生(中文) 林牧頴
研究生(英文) Mu-Yin Lin
學號 N26061628
學位類別 碩士
語文別 中文
論文頁數 54頁
口試委員 指導教授-戴政祺
口試委員-楊弘吉
口試委員-李宗勳
口試委員-林育勳
中文關鍵字 渦電流  非破壞性檢測  支持向量機 
英文關鍵字 eddy current  non-destructive  support vector machine 
學科別分類
中文摘要 本論文旨為應用渦電流檢測技術建立一套非破壞性金屬薄膜厚度檢測系統,並結合SVR回歸運算以降低於厚度預估時所產生的誤差,進而減少產品生產時的浪費。電路板生產時,表層銅箔厚度為十分重要影響參數,尤其應用於高頻時,如厚度與原訂規格不同,將會導致電路特性改變,故本文以渦電流線圈感測器置於不同厚度銅箔上時將會對應到不同的阻抗值做為發想,採用訊號之相位與振幅做為特徵值,搭配SVR回歸,以推算出待測物之實際厚度。以SVM為基礎延伸而來的SVR回歸,相較於類神經迴歸運算,能在保有相當的精確度下,進一步減少計算所需的時間,而相較於最小二乘法,其能夠有效增加預估精準度,故更為適合應用於線上檢測系統。藉著數學軟體對預測效果進行模擬,結果顯示,SVR 回歸確實能有效減少預估誤差量。最後於實時實驗結果顯示,藉著本文所建立之系統進行厚度預估可有效將相對誤差降低75%以上。
英文摘要 This paper aims at establishing a set of non-destructive copper coating thickness detection system using eddy current technology, and combine Support Vector Regression (SVR) operation to reduce the error caused by thickness estimation, thereby reducing waste in production. When the print circuit board (PCB) is produced, the thickness of the surface copper coating is a very important parameter. Especially when it is applied to high frequency products, if the copper thickness is different from the original specification, the circuit characteristics will change. Therefore, based on the fact that copper coating with different thicknesses will correspond to different impedance values to the probe, this paper takes signal phase and amplitude as characteristic values, and uses SVR to estimate the thickness of the object to be tested. The SVR based on Support Vector Machine (SVM) can reduce the time required for calculations while maintaining considerable accuracy compared with the neural network. On the other hand, SVR also has better accuracy than the least squares method. Hence, it is more suitable for online detection systems. The whole process is simulated and the results show that SVR can effectively reduce the amount of prediction error. The final experimental results also show that the thickness estimation by the system established in this paper can effectively reduce the relatively error by more than 75%.
論文目次 目錄
摘要 III
Extended Abstract IV
致謝 XI
圖目錄 XIV
表目錄 XVI
第一章 緒論 1
1-1 研究背景 1
1-2 國內外文獻回顧 2
1-3 研究動機與目的 5
1-4 論文架構 6
第二章 渦電流檢測與電磁感應原理 7
2-1 簡介 7
2-2 電磁感應原理與影響量測因素分析 7
2-2-1 電磁感應原理 7
2-2-2 影響量測因素分析 8
2-3 感應線圈之電磁特性分析 9
2-3-1 線圈磁場原理分析 9
2-3-2 線圈諧振頻率以及待測物對其阻抗影響分析 11
第三章 系統架構與設計 15
3-1 前言 15
3-2 系統架構設計說明 15
3-2-1 弦波產生電路 16
3-2-2 探頭驅動電路 17
3-2-3 訊號運算電路 18
3-2-4 微處理機 21
3-3 支持向量機(SVM)介紹與回歸應用 24
3-3-1 支持向量機介紹 24
3-3-2 核函數(Kernel Function)介紹 25
3-3-3 支持向量回歸(Support Vector Regression) 27
3-4 模擬與測試 28
第四章 系統實驗與結果討論 32
4-1 簡介 32
4-2 系統軟體架構與運作流程 32
4-3 硬體電路與探頭規格介紹 34
4-4 線上量測結果與比較 42
4-5 結果分析 48
第五章 結論與未來展望 50
5-1 結論 50
5-2 未來研究方向 51
參考文獻 52
參考文獻 [1] C. C. Tai and J. H. Rose, “Thickness and conductivity of metallic layers from pulsed eddy-current measurements” Review of Scientific Instruments, Vol. 67, No.11, pp. 3965-3972, 1996.
[2] J. F. Coste and F. Lakestani, “Description of a method for the measurement of the Rayleigh wave velocity: application to the thickness measurement of metallic coatings” 1994 Proceedings of IEEE Ultrasonics Symposium, Vol. 2, pp. 1233-1236, 1994.
[3] M. T. Ghasr and M. J. Horst, “Accurate One-Sided Microwave Thickness Evaluation of Lined-Fiberglass Composites” IEEE Transactions on Instrumentation and Measurement, Vol. 64, pp. 2802-2812, Oct. 2015.
[4] T. Ying, P. Meng, and C. FeiLu, “Feature extraction based on the principal component analysis for pulsed magnetic flux leakage testing” 2011 International Conference on Mechatronic Science, Electric Engineering and Computer (MEC), pp. 2563-2566, 2011.
[5] C. C. Tai, “Characterization of coatings on magnetic metal using the swept frequency eddy current method” Review of Scientific Instruments, Vol. 71, pp. 3161-3167, 2000.
[6] 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, Jan. 2002.
[7] 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.8, pp. 1259-1265, July 2002.
[8] 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.
[9] 王勝豐,「有限元素法分析掃頻式和脈衝式渦電流檢測」,國立成功大學電機工程學系碩士論文,2003。
[10] 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, pp. 347-350, 2012.
[11] 翁新發,「基於諧振原理之渦電流檢測儀設計與使用」,國立成功大學電機工程學系碩士論文,2012。
[12] 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。
[13] 蔡侑侖,「非接觸式微米級印刷電路板銅箔厚度量測系統及多品質特性之最佳感測線圈設計」,國立成功大學電機工程學系碩士論文,2018。
[14] K. Tsukada, M. Hayashi, Y. Nakamura, K. Sakai, and T. Kiwa, “Small Eddy Current Testing Sensor Probe Using a Tunneling Magnetoresistance Sensor to Detect Cracks in Steel Structures” IEEE Transactions on Magnetics, Vol. 54, no. 11, pp. 1-5, Nov. 2018.
[15] N. Yusa, H. Hashizume, and R. Urayama, “An arrayed uniform eddy current probe design for crack monitoring and sizing of surface breaking cracks with the aid of a computational inversion technique” NDT & E International, Vol. 61, pp. 29-34, 2014.
[16] Z. Qu, Q. Zhao, and Y. Meng, “Improvement of sensitivity of eddy current sensors for nano-scale thickness measurement of Cu films” NDT & E International, Vol 61, 2014, pp. 53-57.
[17] C. Tai and Y. Pan, “A Novel Multiphysics Sensoring Method Based on Thermal and EC Techniques and Its Application for Crack Inspection” 2008 IEEE International Conference on Sensor Networks, Ubiquitous, and Trustworthy Computing (sutc 2008), Taichung, pp. 475-479, 2008.
[18] H. Wang and Z. Feng, “Ultrastable and highly sensitive eddy current displacement sensor using self-temperature compensation” Sensors and Actuators A: Physical, Vol. 203, pp. 362-368, 2013.
[19] A. Lopes Ribeiro, H. Geirinhas Ramos, and J. Couto Arez, “Liftoff insensitive thickness measurement of aluminum plates using harmonic eddy current excitation and a GMR sensor” Measurement, Vol. 45, Issue 9, pp. 2246-2253, 2012.
[20] M. Fan and B. Cao, “Elimination of liftoff effect using a model-based method for eddy current characterization of a plate” NDT & E International, Vol. 74, pp. 66-71, 2015.
[21] E. Pinotti and E. Puppin, “Simple Lock-In Technique for Thickness Measurement of Metallic Plates” IEEE Transactions on Instrumentation and Measurement, Vol. 63, no. 2, pp. 479-484, Feb. 2014.
[22] L. S. Rosado, F. M. Janeiro, P. M. Ramos, and M. Piedade, “Defect Characterization With Eddy Current Testing Using Nonlinear-Regression Feature Extraction and Artificial Neural Networks” IEEE Transactions on Instrumentation and Measurement, Vol. 62, no. 5, pp. 1207-1214, May 2013.
[23] A. Bernieri, L. Ferrigno, M. Laracca, and M. Molinara, “Crack Shape Reconstruction in Eddy Current Testing Using Machine Learning Systems for Regression” IEEE Transactions on Instrumentation and Measurement, Vol. 57, no. 9, pp. 1958-1968, Sept. 2008.
[24] G. D’Angelo, M. Laracca, S. Rampone, and G. Betta, “Fast Eddy Current Testing Defect Classification Using Lissajous Figures” IEEE Transactions on Instrumentation and Measurement, Vol. 67, no. 4, pp. 821-830, Apr. 2018.
[25] Sarah M. Erfani, S. Rajasegarar, S. Karunasekera, and C. Leckie, “High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning” Pattern Recognition, Vol. 58, pp. 121-134, 2016.
[26] B. Kuo, H. Ho, and C. Li, “A Kernel-Based Feature Selection Method for SVM With RBF Kernel for Hyperspectral Image Classification” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 7, no. 1, pp. 317-326, Jan. 2014.
[27] X. Liu and J. Tang, “Mass Classification in Mammograms Using Selected Geometry and Texture Features, and a New SVM-Based Feature Selection Method” IEEE Systems Journal, Vol. 8, no. 3, pp. 910-920, Sept. 2014.
[28] O. Bíró, “Edge element formulations of eddy current problems” Computer Methods in Applied Mechanics and Engineering, Vol. 169, Issues 3-4, pp. 391-405, 1999.
[29] J. García-Martín, J. Gómez-Gil, and E. Vázquez-Sánchez, “Non-Destructive Techniques Based on Eddy Current Testing” Sensors, Vol.11, Issues 3, PP. 3525-2565, 2011.
[30] 戴政祺,「非破壞性檢測」上課講義,國立成功大學電機系。
[31] “AD9851 Datasheet” Analog Devices, Inc.
[32] “AD637 Datasheet” Analog Devices, Inc.
[33] C. Cortes and V.Vapnik, “Support-vector networks” Machine learning, Vol. 20, Issus 3, pp. 273-297, 1995.
[34] Burges and Christopher JC., “A tutorial on support vector machines for pattern recognition” Data mining and knowledge discovery, pp. 121-167, 1998.
[35] Boser, Bernhard E., Isabelle M. Guyon, and Vladimir N. Vapnik, “A training algorithm for optimal margin classifiers” Proceedings of the fifth annual workshop on Computational learning theory, 1992.
[36] C. C. Chang and C. J. Lin, “LIBSVM : a library for support vector machines”, ACM Transactions on Intelligent Systems and Technology, 2011.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2024-07-25起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2024-07-25起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw