請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/80707完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 吳政忠(Tsung-Tsong Wu) | |
| dc.contributor.author | Pi-Yun Chang | en |
| dc.contributor.author | 張必昀 | zh_TW |
| dc.date.accessioned | 2022-11-24T03:13:35Z | - |
| dc.date.available | 2021-11-05 | |
| dc.date.available | 2022-11-24T03:13:35Z | - |
| dc.date.copyright | 2021-11-05 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-10-21 | |
| dc.identifier.citation | M. Afzal, S. Udpa, 'Advanced signal processing of magnetic flux leakage data obtained from seamless gas pipeline,' NDT E Int., 35 (7) (2002), pp. 449-457. S. Saha, S. Mukhopadhyay, U. Mahapatra, S. Bhattacharya, G.P. Srivastava, 'Empirical structure for characterizing metal loss defects from radial magnetic flux leakage signal,' NDT E Int., 43 (6) (2010), pp. 507-512. L. Udpa, S. Udpa, A. Tamburrino, 'Adaptive wavelets for characterizing magnetic flux leakage signals from pipeline inspection,' IEEE Trans. Magn., 42 (10) (2006), pp. 3168-3170. J. Garcia-Martin, J. Gomez-Gil, E. Vasquez-Sanchez,'Non-destructive techniques based on eddy current testing,' Sensors, 11 (2011), pp. 2525-2565. V. Sundararaghavan, K. Balasubramaniam, N.R. Babu, N. Rajesh,' A multi-frequency eddy current inversion method for characterizing conductivity gradients on water jet peened components,' NDT E Int., 38 (7) (2005), pp. 541-547. G.Y. Tian, A. Sophian, D. Taylor, J. Rudlin,' Multiple sensors on pulsed eddy-current detection for 3-D subsurface crack assessment,' IEEE Sens. J., 5 (1) (2005), pp. 90-96. Y. He, G. Tian, H. Zhang, M. Alamin, A. Simm, P. Jackson,' Steel corrosion characterization using pulsed eddy current systems,' IEEE Sens. J., 12 (6) (2012), pp. 2113-2120. M. Hirao, H. Ogi,' An SH-wave EMAT technique for gas pipeline inspection,' NDT E Int., 32 (3) (1999), pp. 127-132. S. Dixon, S.B. Palmer,' Wideband low frequency generation and detection of Lamb and Rayleigh waves using electromagnetic acoustic transducers (EMATs),' Ultrasonics, 42 (2004), pp. 1129-1136. J. M. Liu,' emperature Dependence of Elastic Stiffness in Aluminum Alloys Measured with Non-Contact Electromagnetic Acoustic Transducers (EMATS),' IEEE 1984 Ultrasonics Symposium, (1984), pp. 972-974 Francisco Hernandez-Valle, Steve Dixon,' Initial tests for designing a high temperature EMAT with pulsed electromagnet,' NDT E International, Volume 43, Issue 2, (2010), pp. 171-175. P.A. Petcher, M.D.G. Potter, S. Dixon,' A new electromagnetic acoustic transducer (EMAT) design for operation on rail,' NDT E International, Volume 65, (2014), pp. 1-7. H. Gao, B. Lopez, X. Minguez and Jianbin Chen,' Ultrasonic inspection of partially completed welds using EMAT-generated surface wave technology,' 2015 IEEE Far East NDT New Technology Application Forum (FENDT), (2015), pp. 263-266. Liang Cheng, Maria Kogia, Abbas Mohimi, Vassilios Kappatos, Cem Selcuk, Tat-Hean Gan,' Crack characterisation using invariable feature extraction in stainless steel specimen used for absorber tubes of CSP applications via EMAT,' Renewable Energy, Volume 101, (2017), pp. 771-781. Tianhao Liu, Cuixiang Pei, Rui Cai, Yong Li, Zhenmao Chen,' A flexible and noncontact guided-wave transducer based on coils-only EMAT for pipe inspection,' Sensors and Actuators A: Physical, Volume 314, (2020), 112213. D. Silver et al.,' Mastering the game of Go with deep neural networks and tree search,' Nature, vol. 529, no. 7587, (2016), pp. 484-489. D. Silver et al.,' Mastering the game of go without human knowledge,' Nature, vol. 550, no. 7676, (2017), pp. 354-359. G. E. Hinton and R. R. Salakhutdinov,' Reducing the dimensionality of data with neural networks,' science, vol. 313, no. 5786, (2006), pp. 504-507. A. Krizhevsky, I. Sutskever, and G. E. Hinton,' Imagenet classification with deep convolutional neural networks,' in Advances in neural information processing systems, (2012), pp. 1097-1105. K. He, X. Zhang, S. Ren, and J. Sun,' I Deep residual learning for image recognition,' in Proceedings of the IEEE conference on computer vision and pattern recognition, (2016), pp. 770-778. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner,' Gradient-based learning applied to document recognition,' Proceedings of the IEEE, vol. 86, no. 11, (1998), pp. 2278-2324. C. Szegedy et al.,' Going deeper with convolutions,' in Proceedings of the IEEE conference on computer vision and pattern recognition, (2015), pp. 1-9. K. Cho et al.,' Learning phrase representations using RNN encoder-decoder for statistical machine translation,' arXiv preprint arXiv:1406.1078, (2014). J. Chung, K. Kastner, L. Dinh, K. Goel, A. C. Courville, and Y. Bengio,' A recurrent latent variable model for sequential data,' in Advances in neural information processing systems, (2015), pp. 2980-2988. S. Legendre, D. Massicotte, J. Goyette and T. K. Bose,' Neural classification of Lamb wave ultrasonic weld testing signals using wavelet coefficients,' in IEEE Transactions on Instrumentation and Measurement, vol. 50, no. 3, June (2001), pp. 672-678. Y. Yan, D. Liu, B. Gao, G. Y. Tian and Z. C. Cai,' A Deep Learning-Based Ultrasonic Pattern Recognition Method for Inspecting Girth Weld Cracking of Gas Pipeline,' in IEEE Sensors Journal, vol. 20, no. 14, July15, (2020), pp. 7997-8006. J.D.Achenbach,' Wave propagation in elastic solids,'(1973) , pp. 246 P. Xin, Lianwen Yang and Yongke Li,' Mechanism and application of EMAT technology based on NDT,' 2014 China International Conference on Electricity Distribution (CICED), (2014), pp. 100-102. A.G. Olabi, A. Grunwald,' Design and application of magnetostrictive materials,' Materials Design, Volume 29, Issue 2, (2008), pp. 469-483. K. P. BELOV,' The Great Soviet Encyclopedia,' 3rd Edition (1970-1979). | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/80707 | - |
| dc.description.abstract | 在螺絲製作時，會發現某些螺絲強度特別低，問題來源為製作的鐵條本身就存在一些細小的缺陷，導致利用到包含缺陷的材料時，會有螺絲強度不足的狀況產生。因此，要如何及時且快速的，將包含缺陷的鐵條篩檢出來，成為了生產者最重要的課題。此時利用電磁聲波檢測法此種非破壞檢測的方式，便成為最佳的選擇，此種探頭製作便利且成本低廉，操作方式簡便易學，透過探頭在鐵條上激發出彈性波訊號，使其在鐵條中傳遞，再利用探頭接收訊號，便可從中判斷出其中有無包含缺陷反射訊號，然而，低信噪比的缺點，一直都是此探頭的硬傷。 因此，本研究透過結合深度學習，達到實現人工智慧的要求，透過機器的自我學習，歸納出一系列判讀缺陷反射訊號的方法。其中，又以卷積式類神經網路，在辨識圖像上，有最好的表現結果，透過其特有的卷積以及池化層，能夠先將圖片特徵提取出來，以利全連階層進行歸納統整。透過此項技術結合電磁聲波換能器，並探討最好的資料處理方法，以及最佳的卷積式類神經網路模型架構，最後設計出一個最完善的判讀模型。 本研究所量測的鐵條直徑為3.5mm，量測缺陷深度從1mm~0.6mm，準確率可以到達97.4%，並且在判斷缺陷準確率為92.31%，判斷沒有缺陷的準確率為98.44%。同時，在確保有無缺陷的比數不會相差過於懸殊的狀況下，利用訊號相減的方法，模擬出無邊界鐵條時，應該要量測到的訊號模式，在受限於實驗試體的有限長度的狀況下，盡可能地貼近實際應用情形。 經透過硬體與軟體的配合，建構出一套最佳的判斷缺陷反射訊號模型，在即時、且簡便的前提下，解決判讀訊號時，因量測訊號信噪比過低，需要依賴專業知識人員的困境，讓此檢測模式可以廣泛的應用於鐵條缺陷的檢測上，減少螺絲後續的品管成本。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-24T03:13:35Z (GMT). No. of bitstreams: 1 U0001-1810202109415700.pdf: 4889745 bytes, checksum: 087dea2c9c1a62c1360fea41b438b3ce (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | 致謝 I 中文摘要 II ABSTRACT III 目錄 V 圖目錄 VII 表目錄 X 第一章 導論 1 1.1 研究動機 1 1.2 文獻回顧 2 1.3 章節介紹 5 第二章 電磁聲波換能器原理及應用 7 2.1 電磁聲波換能器介紹 7 2.2 電磁聲波換能器原理 7 2.2.1 勞倫茲力 8 2.2.2 磁致伸縮力 8 2.3 電磁聲波換能器量測架構及探頭比較 9 2.3.1 實驗及電磁生波換能器探頭架構 10 2.3.2 實驗訊號頻率分析以及波速計算 11 2.3.3 永久磁鐵擺放距離與線圈匝數比較 12 第三章 人工智慧簡介及類神經網路應用 27 3.1 類神經網路架構 27 3.1.1 深度類神經網路 27 3.1.2 卷積式類神經網路 29 3.1.3 反向傳播法 31 3.2 類神經網路中應用參數介紹 35 3.2.1 活化函數 35 3.2.2 學習速率 37 3.2.3 優化器 38 3.2.4 L2正則項 39 3.3 卷積式類神經網路架構 40 第四章 缺陷實驗與人工智慧判讀結果 50 4.1 實驗資料擷取與分類方法 50 4.1.1 實驗資料擷取 50 4.1.2 訓練資料分類方法 51 4.2 不同資料前處裡方法之訓練結果比較 52 4.2.1 訊號有無平均比較 52 4.2.2 縮短取樣視窗 53 4.2.3 消除24 μs取樣視窗反射訊號 55 4.3 最佳化卷積式類神經網路 57 4.3.1 卷積以及池化層比較 57 4.3.2 全連接層層數以及神經元個數比較 58 4.3.3 L2正則項訓練結果探討 59 第五章 結論與外來展望 77 5.1 結論 77 5.2 未來展望 80 參考文獻 81 | |
| dc.language.iso | zh-TW | |
| dc.subject | 人工智慧 | zh_TW |
| dc.subject | 非破壞檢測 | zh_TW |
| dc.subject | 電磁聲波換能器 | zh_TW |
| dc.subject | 卷積式類神經網路 | zh_TW |
| dc.subject | Electromagnetic acoustic transducer | en |
| dc.subject | Nondestructive testing | en |
| dc.subject | Convolutional neural network | en |
| dc.subject | Artificial intelligence | en |
| dc.title | 以人工智慧輔助電磁超聲波在鐵條缺陷檢測之研究 | zh_TW |
| dc.title | A Study on the Crack Detection of Steel Rod Using AI-assisted Electromagnetic Acoustic Wave Measurement | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.coadvisor | 劉佩玲(Pei-Ling Liu) | |
| dc.contributor.oralexamcommittee | 張瑞益(Hsin-Tsai Liu),孫嘉宏(Chih-Yang Tseng) | |
| dc.subject.keyword | 非破壞檢測,電磁聲波換能器,人工智慧,卷積式類神經網路, | zh_TW |
| dc.subject.keyword | Nondestructive testing,Electromagnetic acoustic transducer,Artificial intelligence,Convolutional neural network, | en |
| dc.relation.page | 84 | |
| dc.identifier.doi | 10.6342/NTU202103807 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2021-10-22 | |
| dc.contributor.author-college | 工學院 | zh_TW |
| dc.contributor.author-dept | 應用力學研究所 | zh_TW |
| 顯示於系所單位： | 應用力學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-1810202109415700.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 4.78 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。