研究生: |
邱正宇 Jeng-Yu Chiou |
---|---|
論文名稱: |
石墨烯/PVDF螺旋式壓電感測器的多受力模式K-mer辨識與力量測 K-mer-based Recognition of Multiple Load Conditions and Force Measurement Using Graphene/PVDF Helical Sensor |
指導教授: |
林柏廷
Po-Ting Lin |
口試委員: |
林柏廷
Po-Ting Lin 張敬源 Ching-Yuan Chang 洪維松 Wei-Song Hung 吳育瑋 Yu-Wei Wu |
學位類別: |
碩士 Master |
系所名稱: |
工程學院 - 機械工程系 Department of Mechanical Engineering |
論文出版年: | 2023 |
畢業學年度: | 112 |
語文別: | 中文 |
論文頁數: | 106 |
中文關鍵詞: | 石墨烯/PVDF 壓電薄膜 、螺旋形感測器 、標準化量測 、穿戴式裝置 |
外文關鍵詞: | Graphene-PVDF Piezoelectric Film, Helical Shape Sensor, Standardized Measurements, Wearable Device |
相關次數: | 點閱:28 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
因應工業 4.0及大數據時代的需求,藉由感測器獲取時序序列資料已是相當廣泛的方法,而感測器的應用如:智慧型手機及手錶的人體動態識別也日益常見,本論文所設計的石墨烯/PVDF 壓電螺旋形感測器能夠因應多種不同的外力透過石墨烯/PVDF 壓電薄膜產生不同波型的電壓時序資料,藉此判斷不同的外力種類。
本論文所設計之石墨烯/PVDF 壓電螺旋形感測器為新型的感測器,因此藉由五種不同的外力標準化實驗,以量測在不同的外力種類及大小下電壓信號變化,並建立外力大小與電壓信號的函數關係以利後續量測外力時使用,藉這些量測到的信號,透過特殊的信號採樣方式以及信號前處理方式以機器學習中的隨機森林演算法、支持向量機(SVM)、K-近鄰演算法(KNN)進行學習採樣特定時間長短的電壓資料,再透過十折交互驗證得到辨識率及標準差為 92.82%(± 1.07%)的分類模型。
本論文最後藉由熱塑性聚氨酯(TPU)所設計之穿戴式裝置與石墨烯/PVDF 壓電螺旋形感測器組合後,配戴於手臂、手腕及手指,藉由手的不同動作對感測器產生不同外力,以造成與標準化相似的電壓信號,該電壓信號透過分類模型後辨識率為 83.97%(± 0.85%),並且透過量測受力與電壓信號間的函數關係量測外力。
In response to the demands of Industry 4.0 and the era of big data, the acquisition of timeseries data through sensors has become a widely adopted method. The application of sensors in body dynamics recognition, such as in smart phones and smart watches, is increasingly common. The designed graphene/ PVDF piezoelectric helical sensor in this thesis can generate voltage time-series data with different waveforms in response to various external forces through the graphene/PVDF piezoelectric film, enabling the identification of different types of external forces.
The designed graphene/PVDF piezoelectric helical sensor in this thesis is a novel type of sensor. Therefore, through five different standardized experiments involving external forces, measurements were taken to observe voltage signal variations under different types and magnitudes of external forces. The functional relationship between external force magnitude and voltage signal was established to facilitate subsequent force measurements. Using the acquired signals, machine learning algorithms, including Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN), were applied with special signal sampling and preprocessing methods to learn and sample voltage data of specific time durations. Through a ten-fold cross-validation, a classification model with an accuracy rate of 92.82% (±1.07%) was obtained.
Finally, this thesis employed a wearable device designed with thermoplastic polyurethane (TPU) and integrated it with the graphene/PVDF piezoelectric helical sensor. The wearable device was worn on the arm, wrist, and finger, generating different external forces through various hand postures. This resulted in voltage signals resembling the standardized patterns. The recognition rate of the voltage signals through the classification model was 83.97%(±0.85% ), and the force was measured through the functional relationship between force and voltage signals.
[1] M. A. Kaleem, M. Khan, Significance of additive manufacturingfor industry 4.0 with introduction of artificial intelligence in additive manufacturing regimes, 2020 17th International Bhurban Conference on Applied Sciences and Technology (IBCAST), 152-156, 2020.
[2] J. Yan, Y. Meng, L. Lu, L. J. I. A. Li, Industrial big data in an industry 4.0 environment: Challenges, schemes, and applications for predictive maintenance, 5, 23484-23491, 2017.
[3] T. Kalsoom, N. Ramzan, S. Ahmed, M. J. S. Ur-Rehman, Advances in sensor technologies in the era of smart factory and industry 4.0, 20(23), 6783, 2020.
[4] L. Georgios, S. Kerstin, A. Theofylaktos, Internet of things in the context of industry 4.0: An overview, 2019.
[5] Y. Zhou, P. Zhan, M. Ren, G. Zheng, K. Dai, L. Mi, C. Liu, C. J. A. a. m. Shen, interfaces, Significant stretchability enhancement of a crack-based strain sensor combined with high sensitivity and superior durability for motion monitoring, 11(7), 7405-7414, 2019.
[6] J. Chen, J. Zheng, Q. Gao, J. Zhang, J. Zhang, O. M. Omisore, L. Wang, H. J. A. S. Li, Polydimethylsiloxane (PDMS)-based flexible resistive strain sensors for wearable applications, 8(3), 345, 2018.
[7] J. F. Tressler, S. Alkoy, R. E. J. J. o. e. Newnham, Piezoelectric sensors and sensor materials, 2, 257-272, 1998.
[8] S.-M. Chang, H. Muramatsu, C. Nakamura, J. J. M. S. Miyake, E. C, The principle and applications of piezoelectric crystal sensors, 12(1-2), 111-123, 2000.
[9] J. Mrazek, S. J. A. o. t. N. Y. A. o. S. Karlin, Detecting Alien Genes in Bacterial Genomes a, 870(1), 314-329, 1999.
[10] S. Kariin, C. J. T. i. g. Burge, Dinucleotide relative abundance extremes: a genomic signature, 11(7), 283-290, 1995.
[11] S. Orozco-Arias, M. S. Candamil-Cortés, P. A. Jaimes, J. S. Piña, R. Tabares-Soto, R. Guyot, G. J. P. Isaza, K-mer-based machine learning method to classify LTRretrotransposons in plant genomes, 9, e11456, 2021.
[12] 林新翔, 基於 K-mer 深度學習於旋轉圖像之影像辨識方法, 國立臺灣科技大學.
[13] 姚佑達, 基於二階段多保真最佳化之智慧影像辨識方法, 國立臺灣科技大學, 2020.
[14] 張皓崴, 基於 K-mer 圖像特徵生成影像資料擴增, 國立臺灣科技大學, 2021.
[15] 葉致和, 多維度 K-mer 辨識技術之研究:1D K-mer 信號辨識及 2.5D K-mer 物體辨識, 國立臺灣科技大學, 2022.
[16] H. Zhou, Y. Zhang, Y. Qiu, H. Wu, W. Qin, Y. Liao, Q. Yu, H. J. B. Cheng, Bioelectronics, Stretchable piezoelectric energy harvesters and self-powered sensors for wearable and implantable devices, 168, 112569, 2020.
[17] H. Wang, Z. Li, Z. Liu, J. Fu, T. Shan, X. Yang, Q. Lei, Y. Yang, D. J. J. o. M. C. C. Li, Flexible capacitive pressure sensors for wearable electronics, 10(5), 1594-1605, 2022.
[18] M. Pan, C. Yuan, H. Anpalagan, A. Plummer, J. Zou, J. Zhang, C. Bowen, Soft controllable carbon fibre-based piezoresistive self-sensing actuators, Actuators, 79, 2020.
[19] Q. He, Y. Wu, Z. Feng, W. Fan, Z. Lin, C. Sun, Z. Zhou, K. Meng, W. Wu, J. J. J. o. M. C. A. Yang, An all-textile triboelectric sensor for wearable teleoperated human–machine interaction, 7(47), 26804-26811, 2019.
[20] L. Zhang, J. He, Y. Liao, X. Zeng, N. Qiu, Y. Liang, P. Xiao, T. J. J. o. M. C. A. Chen, A self-protective, reproducible textile sensor with high performance towards human–machine interactions, 7(46), 26631-26640, 2019.
[21] S. Li, X. Xiao, J. Hu, M. Dong, Y. Zhang, R. Xu, X. Wang, J. J. A. A. E. M. Islam, Recent advances of carbon-based flexible strain sensors in physiological signal monitoring, 2(8), 2282-2300, 2020.
[22] A. Youssef, D. Matthews, A. Guzzomi, J. J. S. Pan, Measurement of pressure fluctuations inside a model thrust bearing using PVDF sensors, 17(4), 878, 2017.
[23] 黃琮翰, 智能壓電薄膜之壓力感測系統開發並應用於沖床模具之壽命評估, 國立臺北科技大學, 2019.
[24] 莊承修, 具石墨烯壓電感測器的氣動柔性夾爪設計, 國立臺灣科技大學, 2020.
[25] I. Choudhry, H. R. Khalid, H.-K. J. A. A. E. M. Lee, Flexible piezoelectric transducers for energy harvesting and sensing from human kinematics, 2(10), 3346-3357, 2020.
[26] S. Oren, H. Ceylan, L. J. I. S. L. Dong, Helical-shaped graphene tubular spring formed within microchannel for wearable strain sensor with wide dynamic range, 1(6), 1-4, 2017.
[27] W. Ding, L. Lu, Y. Chen, J. Liu, B. J. C. Yang, Flexible P (VDF-TrFE) shared bottom electrode sensor array assisted with machine learning for motion detection, 10(11), 1094, 2020.
[28] X. Chen, L. Gong, L. Wei, S.-C. Yeh, L. Da Xu, L. Zheng, Z. J. I. T. o. I. I. Zou, A wearable hand rehabilitation system with soft gloves, 17(2), 943-952, 2020.
[29] W. Zhang, L. Yu, L. Ye, W. Zhuang, F. Ma, ECG signal classification with deep learning for heart disease identification, 2018 International Conference on Big Data and Artificial Intelligence (BDAI), 47-51, 2018.
[30] S.-H. Kee, J. J. S. m. Zhu, structures, Using piezoelectric sensors for ultrasonic pulse velocity measurements in concrete, 22(11), 115016, 2013.
[31] H. B. Lee, Y. W. Kim, J. Yoon, N. K. Lee, S.-H. J. S. M. Park, Structures, 3D customized and flexible tactile sensor using a piezoelectric nanofiber mat and sandwich-molded elastomer sheets, 26(4), 045032, 2017.
[32] J. O. Kim, J. G. Lee, H. Y. J. U. Chun, Radial vibration characteristics of spherical piezoelectric transducers, 43(7), 531-537, 2005.
[33] 陳韻安, 不同曲率壓電薄膜感測器的力響應之標準量測及其在柔性夾爪之應用, 國立臺灣科技大學, 2021.
[34] 邱泓昱, 可穩定抓取任意形貌物件的可變構氣動柔性夾爪, 國立臺灣科技大學, 2022.
[35] 楊凱安, 拉線驅動柔性機構的製程與運動分析, 國立臺灣科技大學, 2019.
[36] 博高科儀股份有限公司, JOV-30 真空烘箱.
[37] 閃鑄科技, Creator 3 3D 列印機.
[38] S. Maker, PLA 3D 列印線材.
[39] T. connectivity, 電荷放大器.
[40] N. Instruments, 訊號擷取卡.
[41] Y. Zhou, B. He, Z. Yan, Y. Shang, Q. Wang, Z. J. S. Wang, Touch locating and stretch sensing studies of conductive hydrogels with applications to soft robots, 18(2), 569, 2018.
[42] 錫特工業科技有限公司, S-50N 數位推拉力計.
[43] 台灣智能感測科技, MG996R 伺服馬達.
[44] Sunstar, 10 號 PE 線.
[45] Y. Qureshi, M. Tarfaoui, K. Lafdi, K. J. C. S. Lafdi, Technology, Development of microscale flexible nylon/Ag strain sensor wire for real-time monitoring and damage detection in composite structures subjected to three-point bend test, 181, 107693, 2019.