當硬體設備以及物聯網隨著時代的演進逐漸純熟，基於邊緣運算(Edge Computing)的智慧物聯網架構被提出，解決了以往雲端運算(Cloud Computing)造成伺服器崩潰、傳送大量原始資料過於耗費網路流量等狀況。另一方面，工業中應用廣泛的感應電動機，若突然故障導致工作被迫中斷，將造成後續龐大的問題。在此背景之下，本文提出一套馬達異常振動檢測系統，採用智慧物聯網邊緣運算系統，能準確辨識出馬達缺陷種類。在本文的系統架構中，振動訊號由MEMS振動感測器接收，再將訊號傳遞至微控制器進行預處理，霧運算平台部署事先訓練之機器學習模型，智慧感測模組預處理後的振動資料藉由霧運算平台上之模型進行辨識分類，透過可聯網裝置即可即時監控馬達狀態。在系統驗證方面，以鼠籠式感應電動機作為實驗平台，設計實驗針對常見缺陷種類馬達產生的振動時域、振動頻域特徵進行分析，包含時域特徵對於敲擊的指標性、缺陷頻率對於馬達缺陷檢測的指標性，並使用霧運算平台上之辨識模型診斷馬達缺陷種類，馬達故障辨識的準確率約為98%左右。實驗結果證明了本論文開發之系統在實務上的適用性，對於馬達缺陷之診斷具有良好的參考價值。

Under the innovation of hardware technology and IoT technology, the IoT architecture based on edge computing has been proposed, which overcomes the problems of cloud server crash caused by traditional cloud computing and insufficient network bandwidth for transmitting a large amount of raw data. If a sudden failure of induction motors that are widely used in industry causes the interruption, it will cause huge subsequent problems. Under this background, we propose a motor vibration detection system that adopts the edge computing system, which can accurately identify the types of motor defects. In the system architecture, the vibration signal is preprocessed by a smart sensing module composed of a MEMS vibration sensor and a microcontroller, and the fog computing platform deploys a pre-trained convolutional neural network model. The preprocessed vibration data of the measuring module is identified by the convolutional neural network, and the motor status can be monitored in real time through the connection of the mobile device. In terms of system verification, the squirrel-cage induction motor is used as the experimental platform, and experiments are designed to analyze the vibration time domain characteristics and vibration frequency domain characteristics of motors with common defects, including the index of time domain characteristics for knocking and defect frequency for motor defect detection. Finally, the types of motor defects are diagnosed through the pretrained model on the fog computing platform, and the accuracy rate of motor fault identification is about 98%. The experimental results show that this system is applicable in practice. It has a high reference value for the classification of defects.

[1]L. Atzori, A. Iera and G. Morabito, "The Internet of Things: A Survey", Comput. Netw., vol. 54, no. 15, pp. 2787-2805, 2010.
[2]S. M. R. Islam, D. Kwak, M. H. Kabir, M. Hossain and K. -S. Kwak, "The Internet of Things for Health Care: A Comprehensive Survey," in IEEE Access, vol. 3, pp. 678-708, 2015, doi: 10.1109/ACCESS.2015.2437951. [3] W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, "Edge Computing: Vision and Challenges," IEEE Internet of Things Journal, vol. 3, no. 5, pp. 637-646, 2016, doi: 0.1109/jiot.2016.2579198.
[3]鄭允睿, "應用時頻轉換振動訊號分析於軸承異常監視之研究," 碩士, 機械工程學系所, 國立中興大學, 台中市, 2015. [Online]. Available: https://hdl.handle.net/11296/stv8bu
[4]Q. Liu, X. Liu and G. Chen, "Study on Feature Extraction of High Speed Precision Electric Machine Vibration signal" 2010 International Conference on Image Analysis and Signal Processing, 2010, pp. 466-469, doi: 10.1109/IASP.2010.5476075.
[5]J. Zhou et al., "The Research and Application of Vibration Monitoring Theory for Wind Turbine Generator," 2013 Third International Conference on Instrumentation, Measurement, Computer, Communication and Control, 2013, pp. 366-369, doi: 10.1109/IMCCC.2013.84.
[6]H. Liu, Y. Wang, F. Li, X. Wang, C. Liu, and M. G. Pecht, "Perceptual Vibration Hashing by Sub-Band Coding: An Edge Computing Method for Condition Monitoring," IEEE Access, vol. 7, pp. 129644-129658, 2019, doi: 10.1109/access.2019.2940381.
[7]T. Ince, S. Kiranyaz, L. Eren, M. Askar and M. Gabbouj, "Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks," in IEEE Transactions on Industrial Electronics, vol. 63, no. 11, pp. 7067-7075, Nov. 2016, doi: 10.1109/TIE.2016.2582729.
[8]G. Tang, Y. Wang, Y. Huang, N. Liu, and J. He, "Compound Bearing Fault Detection Under Varying Speed Conditions With Virtual Multichannel Signals in Angle Domain," IEEE Transactions on Instrumentation and Measurement, vol. 69, no. 8, pp. 5535-5545, 2020, doi: 10.1109/tim.2020.2965634.
[9]S. Ghemawat, H. Gobioff and S.-T. Leung, "The Google File System", ACM SIGOPS Oper. Syst. Rev., vol. 37, no. 5, pp. 29-43, 2003.
[10]D. Evans, "The Internet Of Things: How the Next Evolution of the Internet is Changing Everything", vol. 1, pp. 1-11, 2011.
[11]"Cisco global cloud index: Forecast and Methodology 2014–2019 white paper" in , 2014.
[12]W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, "Edge Computing: Vision and Challenges," IEEE Internet of Things Journal, vol. 3, no. 5, pp. 637-646, 2016, doi: 10.1109/jiot.2016.2579198.
[13]K. Kaur, S. Garg, G. S. Aujla, N. Kumar, J. J. P. C. Rodrigues and M. Guizani, "Edge Computing in the Industrial Internet of Things Environment: Software-Defined-Networks-Based Edge-Cloud Interplay," in IEEE Communications Magazine, vol. 56, no. 2, pp. 44-51, Feb. 2018, doi: 0.1109/MCOM.2018.1700622.
[14]S. Sukhmani, M. Sadeghi, M. Erol-Kantarci and A. El Saddik, "Edge Caching and Computing in 5G for Mobile AR/VR and Tactile Internet," in IEEE MultiMedia, vol. 26, no. 1, pp. 21-30, 1 Jan.-March 2019, doi: 10.1109/MMUL.2018.2879591.
[15]G. Jia, G. Han, H. Rao and L. Shu, "Edge Computing-Based Intelligent Manhole Cover Management System for Smart Cities," in IEEE Internet of Things Journal, vol. 5, no. 3, pp. 1648-1656, June 2018, doi: 10.1109/JIOT.2017.2786349.
[16]W. Wang and O. A. Jianu, "A Smart Sensing Unit for Vibration Measurement and Monitoring," IEEE/ASME Transactions on Mechatronics, vol. 15, no. 1, pp. 70-78, 2010, doi: 10.1109/tmech.2009.2016956.
[17]E. Oyekanlu, "Predictive Edge Computing for Time Series of Industrial IoT and Large Scale Critical Infrastructure Based on Open-source Software Analytic of Big Data," 2017 IEEE International Conference on Big Data (Big Data), 2017, pp. 1663-1669, doi: 10.1109/BigData.2017.8258103.
[18]X. Wei et al., "MVR: An Architecture for Computation Offloading in Mobile Edge Computing," 2017 IEEE International Conference on Edge Computing (EDGE), 2017, pp. 232-235, doi: 10.1109/IEEE.EDGE.2017.42.
[19]H. El-Sayed et al., "Edge of Things: The Big Picture on the Integration of Edge, IoT and the Cloud in a Distributed Computing Environment," IEEE Access, vol. 6, pp. 1706-1717, 2018, doi: 10.1109/access.2017.2780087.
[20]P. Mach and Z. Becvar, "Mobile Edge Computing: A Survey on Architecture and Computation Offloading," IEEE Communications Surveys & Tutorials, vol. 19, no. 3, pp. 1628-1656, 2017, doi: 10.1109/comst.2017.2682318.
[21]M. O. Ozcan, F. Odaci, and I. Ari, "Remote Debugging for Containerized Applications in Edge Computing Environments," in 2019 IEEE International Conference on Edge Computing (EDGE), 8-13 July 2019 2019, pp. 30-32, doi: 10.1109/EDGE.2019.00021.
[22]A. Chen, F. -H. Liu and S. -D. Wang, "Data Reduction for Real-time Bridge Vibration Data on Edge," 2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA), 2019, pp. 602-603, doi: 10.1109/DSAA.2019.00077.
[23]G. Qian, S. Lu, D. Pan, H. Tang, Y. Liu, and Q. Wang, "Edge Computing: A Promising Framework for Real-Time Fault Diagnosis and Dynamic Control of Rotating Machines Using Multi-Sensor Data," IEEE Sensors Journal, vol. 19, no. 11, pp. 4211-4220, 2019, doi: 10.1109/jsen.2019.2899396.
[24]L. A. d. S. Pedotti, R. M. Zago, M. Giesbrecht, and F. Fruett, "Low-cost MEMS accelerometer network for rotating machine vibration diagnostics," IEEE Instrumentation & Measurement Magazine, vol. 23, no. 7, pp. 25-33, 2020, doi: 10.1109/MIM.2020.9234762.
[25]M. Looney, "The Power of Low Noise in IoT Smart Sensors," 05-Jan 2017.
[26]林旻杰, "工業物聯網之邊緣運算嵌入式系統設計與軸承狀態即時監測應用," 碩士, 電機工程學系, 國立成功大學, 台南市, 2020. [Online]. Available: https://hdl.handle.net/11296/p9nvy4
[27]F. Rudolf, A. Jornod, J. Bergqvist, and H. Leuthold, "Precision accelerometers with ug resolution," (in eng), Sensors and Actuators A-Physical, article vol. 21-23, pp.297-302, 1990 1990. [Online]. Available: https://reurl.cc/55DZoR
[28]李羿, " MEMS智慧感測器邊緣運算系統設計暨感應電動機之缺陷診斷與辨識應用," 碩士, 電機工程學系, 國立成功大學, 台南市, 2021. [Online]. Available: https://hdl.handle.net/11296/fj35r6
[29]C. Y. Sue, C. L. Hsiao, and C. K. Yeh, "Micromachined Capacitive Vibration Sensor with High Passband Flatness for Condition Based Monitoring," in 2020 IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE), 23-25 Oct. 2020 2020, pp. 144-148, doi: 10.1109/ECICE50847.2020.9301966.
[30]S. M. Corporation, "STM32F427xx/STM32F429xx Datasheet."
[31]A. A. Süzen, B. Duman and B. Şen, "Benchmark Analysis of Jetson TX2, Jetson Nano and Raspberry PI using Deep-CNN," 2020 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), 2020, pp. 1-5, doi: 10.1109/HORA49412.2020.9152915.
[32]汪永文、劉啟欣, 電工機械II: 龍騰文化事業股份有限公司, 2015.
[33]S. Nandi, H. A. Toliyat and X. Li, "Condition Monitoring and Fault Diagnosis of Electrical Motors—A Review," in IEEE Transactions on Energy Conversion, vol. 20, no. 4, pp. 719-729, Dec. 2005, doi: 10.1109/TEC.2005.847955.
[34]P. K. S. Shyam Patidar "An Overview on Vibration Analysis Techniques for the Diagnosis of Rolling Element Bearing Faults," International Journal of Engineering Trends and Technology (IJETT), vol. 4, no. 5, pp. 1804-1809, 2013. [Online]. Available: http://ijettjournal.org/archive/ijett-v4i5p97.
[35]O. R. Seryasat, M. Aliyari shoorehdeli, F. Honarvar and A. Rahmani, "Multi-fault diagnosis of ball bearing using FFT, wavelet energy entropy mean and root mean square (RMS)," 2010 IEEE International Conference on Systems, Man and Cybernetics, 2010, pp. 4295-4299, doi: 10.1109/ICSMC.2010.5642389.
[36]P. K. S. Shyam Patidar "An Overview on Vibration Analysis Techniques for the Diagnosis of Rolling Element Bearing Faults," International Journal of Engineering Trends and Technology (IJETT), vol. 4, no. 5, pp. 1804-1809, 2013. [Online]. Available: http://ijettjournal.org/archive/ijett-v4i5p97.
[37]KAMIEL, Berli P.; MULYANI, Mulyani; SUNARDI, Sunardi. Deteksi cacat bantalan bola pada pompa sentrifugal menggunakan spektrum getaran. Semesta Teknika, 2017, 20.2: 204-215.
[38]XU, Qifa, et al. Imbalanced fault diagnosis of rotating machinery via multi-domain feature extraction and cost-sensitive learning. Journal of Intelligent Manufacturing, 2020, 31.6: 1467-1481.
[39]S. G. Johnson and M. Frigo, "A Modified Split-Radix FFT With Fewer Arithmetic Operations," in IEEE Transactions on Signal Processing, vol. 55, no. 1, pp. 111-119, Jan. 2007, doi: 10.1109/TSP.2006.882087.
[40]JOHNSON, Steven G.; FRIGO, Matteo. A Modified Split-radix FFT with Fewer Arithmetic Operations. IEEE Transactions on Signal Processing, 2006, 55.1: 111-119.
[41]J. R. Stack, T. G. Habetler and R. G. Harley, "Fault classification and fault signature production for rolling element bearings in electric machines," in IEEE Transactions on Industry Applications, vol. 40, no. 3, pp. 735-739, May-June 2004, doi: 10.1109/TIA.2004.827454.
[42]T. Ince, S. Kiranyaz, L. Eren, M. Askar and M. Gabbouj, "Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks," in IEEE Transactions on Industrial Electronics, vol. 63, no. 11, pp. 7067-7075, Nov. 2016, doi: 10.1109/TIE.2016.2582729.
[43]CORTES, Corinna; VAPNIK, Vladimir. Support-vector networks. Machine learning, 1995, 20.3: 273-297.
[44]O. Avilov, S. Rimbert, A. Popov and L. Bougrain, "Deep Learning Techniques to Improve Intraoperative Awareness Detection from Electroencephalographic Signals," 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020, pp. 142-145, doi: 10.1109/EMBC44109.2020.9176228.
[45]LECUN, Yann, et al. "Backpropagation applied to handwritten zip code recognition." Neural computation, 1989, 1.4: 541-551.
[46]Boureau, Y-Lan, Jean Ponce, and Yann LeCun. "A Theoretical Analysis of Feature Pooling in Visual Recognition." Proceedings of the 27th international conference on machine learning (ICML-10). 2010.Angle Domain," IEEE Transactions on Instrumentation and Measurement, vol. 69, no. 8, pp. 5535-5545, 2020, doi: 10.1109/tim.2020.2965634.
[47]W. Shi, J. Cao, Q. Zhang, Y. Li and L. Xu, "Edge Computing: Vision and Challenges," in IEEE Internet of Things Journal, vol. 3, no. 5, pp. 637-646, Oct. 2016, doi: 10.1109/JIOT.2016.2579198.