(3.238.173.209) 您好!臺灣時間:2021/05/08 15:09
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:周子頊
研究生(外文):Tzu-Hsu Chou
論文名稱:應用共振檢測法於產品瑕疵檢測之研究
論文名稱(外文):Study on Resonant Inspection Applied for Product Defect
指導教授:鄭經偉
口試委員:康淵欒家敏
口試日期:2016-07-22
學位類別:碩士
校院名稱:國立中興大學
系所名稱:生物產業機電工程學系所
學門:工程學門
學類:機械工程學類
論文種類:學術論文
論文出版年:2016
畢業學年度:104
語文別:中文
論文頁數:62
中文關鍵詞:共振檢測法共振頻率SVM
外文關鍵詞:Resonant InspectionResonance FrequencySVM
相關次數:
  • 被引用被引用:0
  • 點閱點閱:80
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本研究應用共振檢測法,解決業界上面臨的物體尺寸限制、檢測速度、生物不確定性等瑕疵品檢測問題,以取代傳統上費時費力的人工檢測,同時建立一個有效使用共振檢測法的檢測流程。針對不同的實驗物體,找到其頻譜及共振頻率上的差異,之後以不同的分析方法建立判別模型,以此模型判別物體的瑕疵存在與否。實驗將分別對陶瓷基板、單車輪框、鴨蛋蛋殼進行檢測。
實驗結果得知,以共振檢測法進行檢測,可以從頻譜圖中發現良品與不良品在共振頻率、振幅、波形上的差異與變化,再分別以ROC曲線及支撐向量機(SVM)方法建立分類模型進行結構判別。實驗結果顯示,對於陶瓷基板正常與瑕疵件的判別達到100%檢測正確率。而在鴨蛋蛋殼裂痕檢測,以經驗法則找到裂痕特徵並由ROC曲線判別驗證後達到99%檢測正確率,若直接以SVM方法進行判別則是93%檢測正確率。以共振檢測法進行檢測,除了速度較傳統檢測方式更為快速、準確。對於小型尺寸物件的檢測、應用於農產品的檢測上,皆可成功的進行鑑別。

關鍵字:共振檢測法、共振頻率、SVM。


The purpose of this study was applying resonant inspection to solve the problem of subject size limitations, detection rate and biological randomness, to replace the traditional time-consuming manual inspection, and establish an effective resonance testing process. For different experimental objects, it is to find differences in the spectrum and resonance frequency, then use analysis tools to build models to identify the object defect. Test subjects included ceramic substrate, bike rim and duck eggshell.
The experimental results showed that the resonance frequency, amplitude and waveform between normal parts and defective parts are obvious differently. Using ROC curves and SVM method are to establish a classification model for those differences. The experimental results showed that the ceramic substrate for the determination of normal and defective pieces reaches 100% detection accuracy. In the duck eggshell crack detection, the rule of thumb to find the defect characterized and then use ROC curves for identification can reach 99% detection accuracy, besides, use SVM method to identification reach 93% detection accuracy. Using resonant inspection, it is faster and more accurate than the traditional method, and for quality testing of small components and agricultural product can be successfully identified.

Keywords:Resonant Inspection, Resonance Frequency, SVM


誌謝 i
摘要 ii
Abstract iii
目錄 iv
圖目錄 vi
表目錄 ix
第1章 前言 1
1.1 研究背景 1
1.2 研究目的 4
第2章 文獻探討 5
2.1 共振超聲波頻譜 5
2.2 共振檢測法 8
2.3 共振檢測應用於農業上 10
2.4 支撐向量機 12
第3章 理論分析 14
3.1 自然頻率 14
3.2 單位脈衝響應 16
3.3 頻域訊號 18
3.4 ROC曲線 19
3.5 支撐向量機 21
第4章 材料與方法 25
4.1 實驗材料與設備 25
4.2 實驗方法 30
4.2.1 量測陶瓷基板之頻譜訊號 30
4.2.2 量測單車輪框之頻譜訊號 32
4.2.3 量測裂痕蛋相對完整蛋之特徵變化 33
4.2.4 量測鴨蛋之頻譜訊號 35
第5章 實驗結果 36
5.1 量測陶瓷基板之頻譜訊號 36
5.2 量測單車輪框之頻譜訊號 41
5.3 量測裂痕蛋相對完整蛋之特徵變化 44
5.4 量測鴨蛋之頻譜訊號 48
第6章 結論與建議 57
6.1 結論 57
6.2 建議 59
第7章 參考文獻 60



1.Abbasion, S., Rafsanjani, A., Farshidianfar, A., & Irani, N. (2007). Rolling Element Bearings Multi-Fault Classification Based on the Wavelet Denoising and Support Vector Machine. Mechanical Systems and Signal Processing, 21(7), 2933-2945.
2.ASTM. (2001). E 2001 – 98 Standard Guide for Resonant Ultrasound Spectroscopy for Defect Detection in Both Metallic and Non-metallic Parts.
3.Bono, R. W., Sorensen, S. A., & Stultz, G. R. (2010). New Methodology Applying Resonant Inspection for Quality Testing of Very Small Powder Metal Components.
4.Chang, C.-C., & Lin, C.-J. (2012). Libsvm: A Library for Support Vector Machine, 2001. Software available at http://www. csie. ntu. edu. tw/~ cjlin/libsvm.
5.Cortes, C., & Vapnik, V. (1995). Support-Vector Networks. Machine learning, 20(3), 273-297.
6.De Ketelaere, B., Coucke, P., & De Baerdemaeker, J. (2000). Eggshell Crack Detection Based on Acoustic Resonance Frequency Analysis. Journal of Agricultural Engineering Research, 76(2), 157-163.
7.Deng, X., Wang, Q., Chen, H., & Xie, H. (2010). Eggshell Crack Detection Using a Wavelet-Based Support Vector Machine. Computers and electronics in agriculture, 70(1), 135-143.
8.Haoqi, L., & Fei, R. (2014). Resonant Ultrasound Spectroscopy Offers Unique Advantages as a Nondestructive Test Method. Advanced Materials & Processes, 172(10), 17-19.
9.Hertlin, I., & Schultze, D. (2003). Acoustic Resonance Testing: The Upcoming Volume-Oriented Ndt Method. Paper presented at the III Pan-American Conference for Nondestructive Testing.
10.Hsu, C.-W., Chang, C.-C., & Lin, C.-J. (2003). A Practical Guide to Support Vector Classification.
11.Lai, C., Sun, X., Dasch, C., Harmon, G., & Jones, M. (2011). Quantify Resonance Inspection with Finite Element-Based Modal Analyses. Journal of Vibration and Acoustics, 133(3), 031004.
12.Liu, X. (2001). Direct Bond Copper (Dbc) Ceramic Substrate Processing and Reliability Assessment of Solder Joint Interconnection for Power Chips.
13.LU, W., ZHANG, C., LUO, H., DING, W., & WANG, L. (2015). Micro-Cracks Detection of Eggshells Based on a Magnetostrictive Transducer.
14.Nashat, S., Abdullah, A., & Abdullah, M. (2014). Machine Vision for Crack Inspection of Biscuits Featuring Pyramid Detection Scheme. Journal of Food Engineering, 120, 233-247.
15.Rao, S. S., & Yap, F. F. (1995). Mechanical Vibrations (Vol. 4): Addison-Wesley Reading.
16.SANKARAN, V. H. (2012). Acoustic Resonance Testing Using Transform Decomposition and Support Vector Machines for Efficient and Accurate Detection of Defects in Forged Components.
17.Stultz, G. R., Bono, R. W., & Schiefer, M. I. (2005). Fundamentals of Resonant Acoustic Method Ndt Advances in Powder Metallurgy and Particulate Materials 3.
18.Wang, J., Jiang, R., & Yu, Y. (2004). Relationship between Dynamic Resonance Frequency and Egg Physical Properties. Food research international, 37(1), 45-50.
19.Youden, W. J. (1950). Index for Rating Diagnostic Tests. Cancer, 3(1), 32-35.
20.Zadler, B. J., Le Rousseau, J. H. L., Scales, J. A., & Smith, M. L. (2004). Resonant Ultrasound Spectroscopy: Theory and Application. Geophysical Journal International, 156(1), 154-169. doi: 10.1111/j.1365-246X.2004.02093.x
21.白世煜, 紀偉民, 李仲暐, & 鄭經偉. (2001). 利用聲波檢測鴨蛋外殼裂痕之研究. 農林學報, Volume 50, Issue 4, Page(s) 79-102.
22.艾群. (2000). 音波檢測鳳梨內部品質之評估模式.
23.沈明輝. (1999). 鴨蛋振動頻譜分析.



QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔