臺灣博碩士論文加值系統

自工業4.0 的概念被提出，為了提升製造效率與產品良率，同時降低人力成本與機台無預警停機所造成的虧損，建立實用的狀態診斷系統已然成為各界努力的目標，同時隨著電腦運算能力的提升，人工智慧模型的概念將大幅增加實現此目標的可能性，但現今之研究已漸漸產生過度依賴人工智慧的狀況，可能因過度聚焦於模型參數的調整而使模型變得過於複雜，此外在模型方面係以使用彈性較高的非監督式機器學習模型為本研究所用，此方法因缺乏客觀的量化方式作為訓練效果的評估依據而較少學者直接用以作為診斷模型，適當的量化方法將有助於純非監督式模型的建立並探討最佳模型參數，故本研究將探討領域知識對於模型訓練的助益並建立量化指標作為模型選用依據，最後以應用範圍廣泛之滾珠軸承作為應用對象進行概念的驗證。本研究透過執行轉子不平衡、軸承潤滑流失與軸承潤滑汙染三種失效模擬，並藉由多種感測器蒐集完整且全面的物理訊號，接著使用時域與頻域指標進行特徵萃取，隨後有系統地探討特徵指標與失效狀態間的關係，篩選出靈敏指標建立狀態診斷流程並作為非監督式狀態診斷模型的發展基礎，最後吾人使用自編碼器配合分群演算法建立狀態診斷模型，並根據訓練結果建立一個量化方法以量化自編碼器之訓練效果。根據實驗成果，本研究提出之診斷模型能夠有效分辨軸承之失效種類與程度，且在複合失效中仍然適用，而指標篩選對於訓練效果的提升能在可視化圖形中觀察得知並應用本研究之量化指標獲得驗證。綜合探討結果，本研究成功以領域知識協助建立非監督式診斷模型且首次結合客觀的量化方式評估自編碼器訓練結果，此研究流程可被拓展至其他機具次系統，增進智慧工廠中應用的實務價值。

The qualities of machined products are largely depended on the status of machines in various aspects. As a result, appropriate condition monitoring would be essential for both quality control and longevity assessment. Ball bearings are widely used in rotating components and definitely influence the operation quality of machines. Their faults are one of the main reasons that make machines break down and this problem should be investigated. Recently, with the advance in information technology, pure data driven approaches such as machine learnings have been widely applied in status diagnosis. However, the accuracy of those predictions strongly relys on the original data, which largely depends on the selected sensors and signal features. Furthermore, for unsupervised machine learning schemes, although they could avoid the concern of labelling in training, they lack a quantified evaluation of the training results. How to address these concerns is thus not a trivial issue. In this work, by utilizing ball bearing status diagnosis as the addressed problem, a diagnosis flow is developed to accessing the status of bearings in their imbalance, lubrication, and grease contamination levels based on unsupervised machine learning. Multiple sensors are hired to collect data and various statistical methods are used for data reduction and feature extraction. Through systematic analysis, it is possible to find the most sensitive features. Those indexes are then fed into autoencorder for training the collected data to recognize the possible bearing failure type and status. Then, classification models are used to obtain status labels. Furthermore, the effect of sensor index selection on the clustering efficiency are then also examined. The investigation results show that the hired machine learning method performs well with appropriate feature indexes. Not only the severe levels in the same category, but also between different types of failure can be distinguished. On the other hand, improper feature used would lead to poor and even indistinguishable clustering. Furthermore, a whole diagnosis process flow is proposed for counting possible multiple causes of failures. Finally, a model based on the second norm to quantify the separation level of each cluster is proposed as the measure for training results of autoencoder models. The proposed diagnosis flow should be useful for improving the prediction accuracy on reliability assessment in bearing and rotating machinery related applications.

摘要 I
Abstract II
Extended Abstract III
致謝 XXVII
目錄 XXIX
圖目錄 XXXV
表目錄 XLV
符號說明 XLVII
第一章 緒論 1
1.1 前言 1
1.2 文獻回顧 6
1.2.1 軸承之失效形式 6
1.2.2 軸承之狀態監診 7
1.2.3 人工智慧模型於軸承狀態診斷之應用 8
1.2.4 實驗室相關研究 9
1.2.5 文獻評論 11
1.3 研究動機與目的 13
1.4 研究方法 15
1.5 全文架構 16
第二章 軸承與狀態監控相關研究背景介紹 18
2.1 本章介紹 18
2.2 滾動軸承簡介 19
2.3 機具次系統之狀態監控簡介 24
2.4 監控感測器簡介 33
2.4.1 振動感測器 33
2.4.2 聲波感測器 35
2.4.3 電流感測器 37
2.4.4 溫度感測器 38
2.5 討論與文獻評論 41
2.6 本章結論 43
第三章 人工智慧相關研究背景介紹 44
3.1 本章介紹 44
3.2 類神經網路簡介 45
3.2.1 神經元的組成 45
3.2.2 激勵函數之介紹 46
3.2.3 類神經網路之學習方式 50
3.3 機器學習模型介紹 53
3.3.1 監督式學習模型簡介 53
3.3.2 強化式學習模型簡介 57
3.3.3 非監督式學習模型簡介 58
3.4 人工智慧模型於狀態診斷之應用 62
3.5 討論與文獻評論 66
3.6 本章結論 68
第四章 整體研究概念設計 69
4.1 本章介紹 69
4.2 概念設計 70
4.3 狀態診斷系統之軟硬體環境建立 73
4.4 軸承失效實驗與指標評估 75
4.5 人工智慧模型之應用 77
4.6 本章結論 79
第五章 實驗系統與訊號處理方法之建立 80
5.1 本章介紹 80
5.2 實驗載台之建立 81
5.3 感測器之選用與配置 84
5.3.1 振動感測器的選用與配置 85
5.3.2 聲波感測器的選用與配置 86
5.3.3 電流感測器的選用與配置 88
5.3.4 溫度感測器的選用與配置 89
5.4 訊號擷取設備之選用與配置 92
5.5 訊號處理與特徵萃取 97
5.5.1 時域指標 98
5.5.2 頻域指標 100
5.6 本章結論 102
第六章 轉子不平衡實驗與指標評估 103
6.1 本章介紹 103
6.2 轉子不平衡實驗設計 104
6.3 加速規訊號分析結果 107
6.4 麥克風訊號分析結果 115
6.5 聲射感測器訊號分析結果 121
6.6 比流計訊號分析結果 125
6.7 轉子不平衡之特徵指標評估結果 127
6.8 本章結論 129
第七章 軸承潤滑流失實驗與指標評估 130
7.1 本章介紹 130
7.2 潤滑流失實驗設計 131
7.3 加速規訊號分析結果 133
7.4 麥克風訊號分析結果 141
7.5 聲射感測器訊號分析結果 146
7.6 比流計訊號分析結果 150
7.7 溫度訊號分析結果 152
7.8 潤滑流失之特徵指標評估結果 155
7.9 本章結論 157
第八章 軸承潤滑汙染實驗與指標評估 158
8.1 本章介紹 158
8.2 潤滑汙染實驗設計 159
8.3 加速規訊號分析結果 161
8.4 麥克風訊號分析結果 169
8.5 聲射感測器訊號分析結果 174
8.6 比流計訊號分析結果 178
8.7 溫度訊號分析結果 180
8.8 潤滑汙染之特徵指標評估結果 182
8.9 本章結論 183
第九章 非監督式人工智慧模型於軸承狀態診斷之方法建立 184
9.1 本章介紹 184
9.2 基於特徵指標之軸承狀態診斷流程建立 186
9.3 本研究非監督式診斷架構實現 188
9.3.1 軟硬體環境建置 188
9.3.2 模型訓練流程 189
9.4 模型訓練與診斷結果 194
9.4.1 軸承之轉子不平衡狀態模型訓練結果 196
9.4.2 軸承之潤滑流失狀態模型訓練結果 198
9.4.3 軸承之潤滑汙染狀態模型訓練結果 200
9.4.4 軸承之多重狀態診斷流程之探討 201
9.5 自編碼器訓練效果之量化指標建立 206
9.6 本研究非監督式診斷方法探討 210
9.7 本章結論 215
第十章 結果與討論 216
10.1 全文歸納 216
10.1.1 軸承失效相關實驗與感測器特徵指標評估 216
10.1.2 非監督式人工智慧模型診斷 217
10.2 討論 219
10.2.1 多重感測器於軸承狀態監控之應用 219
10.2.2 感測器特徵指標評估結果探討 220
10.2.3 以領域知識協助人工智慧診斷模型建立 222
10.2.4 多重失效診斷流程的建立 223
10.2.5 自編碼器量化指標建立與應用情境探討 224
10.3 未來展望 226
10.3.1 軸承狀態診斷模型的性能提升 226
10.3.2 非監督式診斷方法的範圍拓展 228
10.3.3 非監督式診斷概念的實務應用 228
第十一章 結論與未來工作 229
11.1 本文結論 229
11.2 本文貢獻 232
11.3 未來工作 234
參考文獻 235
附錄 - 非監督式模型訓練程式碼 244
A. Autoencoder模型訓練程式碼 244
B. K-means模型訓練程式碼 248
C. DBSCAN模型訓練程式碼 250

[1]Y. Lu, “Industry 4.0: A Survey on Technologies, Applications and Open Research Issues,” Journal of Industrial Information Integration, vol. 6, pp. 1-10, Jun. 2017.
[2]Cademix Institute of Technology, Industry 4.0. [Online]. Available: https://www.cademix.org/programs/industry-4-0/. [Accessed Jan. 27, 2021].
[3]Wikipedia, Smart manufacturing. [Online]. Available: https://en.wikipedia.org/wiki/Smart_manufacturing. [Accessed Jan. 27, 2021].
[4]B. Kehoe, S. Patil, P. Abbeel, and K. Goldberg, “A Survey of Research on Cloud Robotics and Automation,” IEEE Transactions on Automation Science and Engineering, vol. 12, no. 2, pp. 398-409, Apr. 2015.
[5]E. Sisinni, A. Saifullah, S. Han, U. Jennehag, and M. Gidlund, “Industrial Internet of Things: Challenges, Opportunities, and Directions,” IEEE Transactions on Industrial Informatics, vol. 14, no. 11, pp. 4724-4734, Nov. 2018.
[6]I. Shin, J. Lee, J. Y. Lee, K. Jung, D. Kwon, B. D. Youn, H. S. Jang, and J. H. Choi, “A Framework for Prognostics and Health Management Applications toward Smart Manufacturing Systems,” International Journal of Precision Engineering and Manufacturing-Green Technology, vol. 5, pp. 535-554, Aug. 2018.
[7]G-Y. Lee, M. Kim, Y-J. Quan, M-S. Kim, T. J. Y. Kim, H-S. Yoon, S. Min, D-H. Kim, J-W. Mun, J. W. Oh, I. G. Choi, C-S. Kim, W-S. Chu, J. Yang, B. Bhandari, C-M. Lee, J-B. Ihn, and S-H. Ahn, “Machine health management in smart factory: A review,” Journal of Mechanical Science and Technology, vol. 32, pp. 987–1009, 2018.
[8]Schaeffler Technologies AG & Co. KG. (2012, Mar. 1). Failure Analysis INA Bearing failure mode archive. [Online]. Available: https://www.schaeffler.com/remotemedien/media/_shared_media/08_media_library/01_publications/schaeffler_2/tpi/downloads_8/tpi_109_de_en.pdf. [Accessed Jan. 27, 2021].
[9]Schaeffler Technologies AG & Co. KG. (2010, Dec. 22). Rolling Bearing Damage: Recognition of damage and bearing inspection. [Online]. Available: https://www.schaeffler.com/remotemedien/media/_shared_media/08_media_library/01_publications/schaeffler_2/publication/downloads_18/wl_82102_3_de_en.pdf. [Accessed Jan. 27, 2021].
[10]C. Scheffer and P. Girdhar, Practical Machinery Vibration Analysis & Predictive Maintenance. Amsterdam, The Netherlands: Elsevier, 2004.
[11]B. Li, M-Y. Chow, Y. Tipsuwan, and J. C. Hung, “Neural-network-based motor rolling bearing fault diagnosis,” IEEE transactions on industrial electronics, vol. 47, no. 5, pp. 1060-1069, 2000.
[12]P. K. Kankar, S. C. Sharma, and S. P. Harsha, “Fault diagnosis of ball bearings using machine learning methods,” Expert Systems with Applications, vol. 38, no.3, pp. 1876-1886, Mar. 2011.
[13]A. K. Jalan and A. R. Mohanty, “Model based fault diagnosis of a rotor–bearing system for misalignment and unbalance under steady-state condition,” Journal of Sound and Vibration, vol. 327, pp. 604-622, Nov. 2009.
[14]W. Caesarendra, A. Widodo, P. H. Thom, B. Yang, and J. D. Setiawan, “Combined Probability Approach and Indirect Data-Driven Method for Bearing Degradation Prognostics,” IEEE Transactions on Reliability, vol. 60, no. 1, pp. 14-20, Mar. 2011.
[15]F. Q. Lauzon, “An introduction to deep learning,” The 11th International Conference on Information Sciences, Signal Processing and their Applications, Montreal, Canada, 2012, pp.1438-1439.
[16]Y. Lei, B. Yang, X. Jiang, F. Jia, N. Li, and A. K. Nandi, “Applications of machine learning to machine fault diagnosis: A review and roadmap,” Mechanical Systems and Signal Processing, vol. 138, no. 106587, 2020.
[17]A. D. Nembhard, J. K. Sinha, A. J. Pinkerton, and K. Elbhbah,“Fault diagnosis of rotating machines using vibration and bearing temperature measurements,” Diagnostyka, vol. 14, no. 3, pp. 45-51, 2013.
[18]R. B. Randall, “Detection and diagnosis of incipient bearing failure in helicopter gearboxes,” Engineering Failure Analysis , vol. 11, no. 2, pp. 177-190, 2004.
[19]P. K. Kankar, S. C. Sharma, and S. P. Harsha, “Fault diagnosis of ball bearings using continuous wavelet transform,” Applied Soft Computing, vol. 11, pp. 2300-2312, 2011.
[20]Y. Lei, J. Lin, Z. He, and Y. Zi, “Application of an improved kurtogram method for fault diagnosis of rolling element bearings,” Mechanical Systems and Signal Processing, vol. 25, pp. 1738-1749, 2011.
[21]A. M. Al-Ghamd and D. Mba, “A comparative experimental study on the use of acoustic emission and vibration analysis for bearing defect identification and estimation of defect size,” Mechanical Systems and Signal Processing, vol. 20, no. 7, pp. 1537-1571, Oct. 2006.
[22]J. Park, S. Kim, J-H. Choi, and S. H. Lee, “Frequency energy shift method for bearing fault prognosis using microphone sensor,” Mechanical Systems and Signal Processing, vol. 147, no. 107068, 2021.
[23]B. Yazici and G. B. Kliman, “An Adaptive Statistical Time–Frequency Method for Detection of Broken Bars and Bearing Faults in Motors Using Stator Current,” IEEE Transactions on Industry Applications, vol. 35, no. 2, pp. 442-452, 1999.
[24]P. W. Tse, Y. H. Peng, and R. Yam, “Wavelet Analysis and Envelope Detection for Rolling Element Bearing Fault Diagnosis—Their Effectiveness and Flexibilities,” Journal of Vibration and Acoustics, vol. 123, no. 3, pp. 303-310, Jul. 2001.
[25]D. Yu, J. Cheng, and Y. Yung, “Application of EMD method and Hilbert spectrum to the fault diagnosis of roller bearings”, Mechanical Systems and Signal Processing, vol.19, pp. 259-270, 2005.
[26]H-H. Lee, N-T. Nguyen, and J-M. Kwon, “Bearing diagnosis using time-domain features and decision tree,” Third International Conference on Intelligent Computing, ICIC 2007, Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence, Qingdao, China, Aug. 21-24, 2007, pp. 952-960.
[27]Z. Wang, Q. Zhang, J. Xiong, M. Xiao, G. Sun, and J. He, “Fault Diagnosis of a Rolling Bearing Using Wavelet Packet Denoising and Random Forests,” IEEE Sensors Journal, vol. 17, no. 17, pp. 5581-5588, Sep. 1, 2017.
[28]A. Moosavian, H. Ahmadi, A. Tabatabaeefar, and M. Khazaee, “Comparison of Two Classifiers; K-nearest Neighbor and Artificial Neural Network, for Fault Diagnosis on a Main Engine Journal-bearing,” Shock and Vibration, vol. 20, no. 2, pp. 263-272, Jan. 2013.
[29]L. Ren, Y. Sun, J. Cui, and L. Zhang, “Bearing remaining useful life prediction based on deep autoencoder and deep neural networks,” Journal of Manufacturing Systems, vol. 48, pp. 71-77, Jul. 2018.
[30]Z. Meng, X. Zhan, J. Li, and Z. Pan, “An enhancement denoising autoencoder for rolling bearing fault diagnosis,” Measurement, vol. 130, pp. 448-454, 2018.
[31]Z. Chen and W. Li, “Multisensor Feature Fusion for Bearing Fault Diagnosis Using Sparse Autoencoder and Deep Belief Network,” IEEE Transactions on Instrumentation and Measurement, vol. 66, no. 7, pp. 1693-1702, Jul. 2017.
[32]F. Zhong, T. Shi, and T. He, “Fault diagnosis of motor bearing using self-organizing maps,” 2005 International Conference on Electrical Machines and Systems, Nanjing, China, Sep. 27-29, 2005, pp. 2411-2414.
[33]孫翊淳, 基於類神經網路之狀態監診系統開發及其在工具機刀具狀態診斷之應用, 國立成功大學機械工程學系碩士論文, 2019.
[34]曾子航, 高速智慧主軸於加工中之熱誤差分析, 國立成功大學機械工程學系碩士論文, 2019.
[35]蔡瑞敏, 多波段微機電加速規整合設計於工具機主軸振動監控應用, 國立成功大學機械工程學系碩士論文, 2018.
[36]黃彥享, 應用於工具機主軸監測之數位微機電感測模組整合設計與驗證, 南臺科技大學機械工程系碩士論文, 2020.
[37]韓伯炫, 機械手臂動態分析、視覺引導、及感測器網路整合於智慧工廠之應用, 國立成功大學機械工程學系碩士論文, 2020.
[38]黃建達, 具任務規劃、人機整合、及狀態監控能力之無人搬運車發展及其於智慧工廠之應用, 國立成功大學機械工程學系碩士論文, 2020.
[39]N. De-Laurentis, A. Kadiric, P. Lugt, and P. Cann, “The influence of bearing grease composition on friction in rolling/sliding concentrated contacts,” Tribology International, vol. 94, pp. 624-632, 2016.
[40]Aktiebolaget SKF, “A BRAVE new world for bearings,” skf.com, para. 2, Nov. 6, 2020. [Online]. Available: https://www.skf.com/group/news-and-events/news/2020/2020-11-06-a-brave-new-world-for-bearings. [Accessed Jan. 27, 2021].
[41]Schaeffler Technologies AG & Co. KG, Bearing products. [Online]. Available: https://medias.schaeffler.us. [Accessed Jan. 27, 2021].
[42]A. W. Morgan and D. Wyllie, “A Survey of Rolling-Bearing Failures,” Proceedings of the Institution of Mechanical Engineers, Conference Proceedings, vol. 184, no. 6, pp. 48-56, 1969.
[43]A. Sharma, M. Amarnath, and P. K. Kankar, “Feature extraction and fault severity classification in ball bearings,” Journal of Vibration and Control, vol. 22, no. 1, pp. 176-192, Apr. 2014.
[44]X. Chen, S. Wang, B. Qiao, and Q. Chen, “Basic research on machinery fault diagnostics: Past, present, and future trends,” Frontiers of Mechanical Engineering, vol. 13, pp. 264-291, Jun. 2018.
[45]R. Roy, R. Stark, K. Tracht, S. Takata, and M. Mori, “Continuous maintenance and the future – Foundations and technological challenges,” CIRP Annals, vol. 65, no. 2, pp. 667-688, 2016.
[46]S. Orhan, A. Osman Er, N. Camuşcu, and E. Aslan, “Tool wear evaluation by vibration analysis during end milling of AISI D3 cold work tool steel with 35 HRC hardness,” NDT & E International, vol. 40, no.2, pp. 121-126, Mar. 2007.
[47]J. C. Jáuregui, J. R. Reséndiz, S. Thenozhi, T. Szalay, Á. Jacsó, and M. Takács, “Frequency and Time-Frequency Analysis of Cutting Force and Vibration Signals for Tool Condition Monitoring,” IEEE Access, vol. 6, pp. 6400-6410, Jan. 2018.
[48]E. Ebrahimi, “Fault diagnosis of Spur gear using vibration analysis,” Journal of American Science, vol. 8, no. 1, pp. 133-138, 2012.
[49]X. Chen and Z. Feng, “Time-Frequency Analysis of Torsional Vibration Signals in Resonance Region for Planetary Gearbox Fault Diagnosis Under Variable Speed Conditions,” IEEE Access, vol. 5, pp. 21918-21926, Oct. 2017.
[50]Y. Kong, T. Wang, and F. Chu, “Meshing frequency modulation assisted empirical wavelet transform for fault diagnosis of wind turbine planetary ring gear,” Renewable Energy, vol. 132, pp. 1373-1388, Mar. 2019.
[51]H. Zoubek, S. Villwock, and M. Pacas, “Frequency Response Analysis for Rolling-Bearing Damage Diagnosis,” IEEE Transactions on Industrial Electronics, vol. 55, no. 12, pp. 4270-4276, Dec. 2008.
[52]D. Wu, J. Wang, H. Wang, H. Liu, L. Lai, T. He, and T. Xie, “An Automatic Bearing Fault Diagnosis Method Based on Characteristics Frequency Ratio,” Sensors, vol. 20, no. 5: 1519, Mar. 2020.
[53]M-K. Liu and P-Y. Weng, “Fault Diagnosis of Ball Bearing Elements: A Generic Procedure based on Time-Frequency Analysis,” Measurement Science Review, vol. 19, no. 4, pp. 185-194, Aug. 2019.
[54]B. Sreejith, A. K. Verma, and A. Srividya, “Fault diagnosis of rolling element bearing using time-domain features and neural networks,” 2008 IEEE Region 10 and the Third international Conference on Industrial and Information Systems, Kharagpur, India, Dec. 2008, pp. 1-6.
[55]J. S. Rapur and R. Tiwari, “Experimental Time-Domain Vibration-Based Fault Diagnosis of Centrifugal Pumps Using Support Vector Machine,” ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering, vol. 3, no. 4: 044501, Dec. 2017.
[56]F. Elasha, M. Greaves, D. Mba, and A. Addali, “Application of Acoustic Emission in Diagnostic of Bearing Faults within a Helicopter gearbox,” Procedia CIRP, vol. 38, pp. 30-36, 2015.
[57]J. Park, S. Kim, J-H. Choi, and S. H. Lee, “Frequency energy shift method for bearing fault prognosis using microphone sensor,” Mechanical Systems and Signal Processing, vol. 147, no. 107068, Jan. 2021.
[58]M. Djeddi, P. Granjon, and B. Leprettre, “Bearing Fault Diagnosis in Induction Machine Based on Current Analysis Using High- Resolution Technique,” 2007 IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives, Cracow, Poland, Sep. 2007, pp. 23-28.
[59]T. Praveen Kumar, M. Saimurugan, R. B. Hari Haran, S. Siddharth, and K. I. Ramachandran, “A multi-sensor information fusion for fault diagnosis of a gearbox utilizing discrete wavelet features,” Measurement Science and Technology, vol. 30, no. 8: 085101, Jun. 2019.
[60]Analog Devices Inc., ADXL001 Breakout Board. [Online]. Available: http://www.analog.com/en/design-center/evaluation-hardware-and-software/evaluation-boards-kits/eval-adxl001.html#eb-overview. [Accessed Feb. 1, 2021].
[61]Instrumentation-Electronics, Microstructure of MEMS Accelerometer. [Online]. Available: http://www.instrumentationtoday.com/mems-accelerometer/2011/08/. [Accessed Feb. 1, 2021].
[62]PCB Piezotronics Inc., Accelerometers/Vibration Sensors. [Online]. Available: http://www.pcb.com/TestMeasurement/Accelerometers. [Accessed Feb. 2, 2021].
[63]Unictron Technologies Corp., Mechanical - Electrical energy transformation in piezoelectric ceramics. [Online]. Available: https://www.unictron.com/piezo/piezoelectric-technologies/. [Accessed Feb. 2, 2021].
[64]MediaCollege.com, Cross-section of condenser microphone. [Online]. Available: https://www.mediacollege.com/audio/microphones/condenser.html. [Accessed Feb. 2, 2021].
[65]Kistler Group, “Acoustic Emission Sensor for high temperature & hazardous areas,” Type 8152C datasheet. [Online]. Available: https://www.kistler.com/files/document/003-120e.pdf?callee=frontend. [Accessed Feb. 2, 2021].
[66]A. Cook, S. Collura, M. Dumont, and T. Urbank, “Continuous Monitoring of Powder Size Distribution using High Temperature ATEX Acoustic Emission Sensors,” 31st Conference of the European Working Group on Acoustic Emission (EWGAE 2014), Dresden, Germany, Sep. 2014.
[67]H. Zou and F. Huang, “A novel intelligent fault diagnosis method for electrical equipment using infrared thermography,” Infrared Physics & Technology, vol. 73, pp. 29-35, Nov. 2015.
[68]R. Pandey, S. Naik, and R. Marfatia, “Image Processing and Machine Learning for Automated Fruit Grading System: A Technical Review,” International Journal of Computer Applications, vol. 81, no. 16, pp. 29-39, Nov. 2013.
[69]T. Kanan, O. Sadaqa, A. Aldajeh, H. Alshwabka, W. AL-dolime, S. AlZu’bi, M. Elbes, B. Hawashin, and M. A. Alia, “A Review of Natural Language Processing and Machine Learning Tools Used to Analyze Arabic Social Media,” 2019 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT), Amman, Jordan, 2019, pp. 622-628.
[70]K. Ikeda, T. Shishid, and S. Viennot, “Machine-Learning of Shape Names for the Game of Go,” Advances in Computer Games, vol. 9525, pp. 247-259, Dec. 2015.
[71]Wikipedia, Overfitting. [Online]. Available: https://en.wikipedia.org/wiki/Overfitting. [Accessed Feb. 18, 2021].
[72]C. J. C. H. Watkins and P. Dayan, “Q-learning,” Machine Learning, vol. 8, pp. 279-292, 1992.
[73]A. J. X. Chen, “The Evolution of Computing: AlphaGo,” Computing in Science & Engineering, vol. 18, no. 4, pp. 4-7, Jul.-Aug. 2016.
[74]Y. Ding, L. Ma, J. Ma, M. Suo, L. Tao, Y. Cheng, and C. Lu, “Intelligent fault diagnosis for rotating machinery using deep Q-network based health state classification: A deep reinforcement learning approach,” Advanced Engineering Informatics, vol. 42, no. 100977, Oct. 2019.
[75]Wikipedia, DBSCAN. [Online]. Available: https://en.wikipedia.org/wiki/DBSCAN#/media/File:DBSCAN-Illustration.svg. [Accessed Feb. 19, 2021].
[76]L. Ren, Y. Sun, J. Cui, and L. Zhang, “Bearing remaining useful life prediction based on deep autoencoder and deep neural networks,” Journal of Manufacturing Systems, vol. 48, pp. 71-77, 2018.
[77]X. Zhao, J. Wu, Y. Zhang, Y. Shi, and L. Wang, “Fault Diagnosis of Motor in Frequency Domain Signal by Stacked De-noising Auto-encoder,” Computers, Materials and Continua, vol. 57, no. 2, pp. 223-242, 2018.
[78]J. Wang, S. Li, Y. Xin, and Z. An, “Gear Fault Intelligent Diagnosis Based on Frequency‑Domain Feature Extraction,” Journal of Vibration Engineering & Technologies, vol. 7, pp. 159-166, 2019.