臺灣博碩士論文加值系統

轉子系統為工具機進給系統中的一部份，是由軸承與轉子組成，其健康與否會影響進給系統之定位精度，因此本研究針對轉子健康狀態分析分成三個部分，第一部分針對軸承原始訊號使用短時傅立葉變換與小波轉換得到與軸承故障有關之時頻圖，利用k階矩抽取特徵。第二部分利用偏心實驗，從全息譜橢圓抽取其面積與偏心率特徵，並診斷轉子裝配狀況。第三部分使用孤立森林演算法訓練軸承健康資料並診斷其當前健康狀態與剩餘壽命。利用PHM與NASA軸承實驗驗證，結果能夠診斷軸承之健康狀況。

The rotor system consisting of bearings and a rotor is a key part of the feed drive system in the machine tools. Its health affects the positioning accuracy and reliability of the feed drive system. The thesis addresses the issues of rotor-bearing health monitoring which includes the bearing health and bearing assembly in the feed drive system. The thesis is divided into three parts. The first part aims at acquiring the bearing vibration signal processed using the short-time Fourier transform and wavelet transform to obtain spectrograms related to the bearing fault. Then the kth-order moment method is used to quantify the variations in spectrograms which are used as features for later unsupervised learning. The second part focuses on the bearing misalignment monitoring. The vibration holospectrum is utilized to quantify the feature related to the bearing misalignments and an experiment is conducted to assess its performance. The third part introduces the isolation forest algorithm used in assessing the bearing current health condition and later predicting the remaining useful life. Both PHM and NASA bearing data from internet are utilized to assess the performance of the proposed methods. Results show that the proposed method can effectively monitor the bearing health and bearing assembly in terms of misalignment in the feed drive system.

表 目 錄 III
圖 目 錄 IV
第一章 緒論 1
1-1 前言 1
1-2 研究動機與目的 1
1-3 文獻回顧 2
1-3-1 軸承診斷技術 2
1-3-2 孤立森林 5
1-3-3 全息譜 6
1-3-4 文獻回顧總結 7
1-4 研究流程與方法 8
第二章 軸承故障特徵擷取與演算法 10
2-1 軸承故障特徵擷取 10
2-1-1 時域與頻域特徵 10
2-1-2 k階moment時頻特徵 11
2-2 孤立森林 14
2-2-1 孤立樹與異常分數 15
2-2-2 孤立森林訓練數量 18
第三章 轉子裝配異常診斷 19
3-1 全息譜介紹 19
3-2 應用全息譜監測旋轉軸組裝與運轉品質 20
3-3 應用全息譜監測轉子對心不平行實驗 21
第四章 軸承診斷與壽命預估實驗 26
4-1軸承實驗數據 26
4-1-1 NASA軸承疲勞實驗 26
4-1-2 PHM軸承疲勞實驗 27
4-2軸承健康診斷與壽命預估之驗證 28
第五章 結論與未來展望 40
5-1研究結論 40
5-2未來研究方向 41
參考文獻...........................................................40

[1]聯宏軸承，http://a16329395.pixnet.net/blog/post/191114819-%E8%BB%B8%E6%89%BF%E7%9A%84%E5%88%86%E9%A1%9E%E5%B0%8F%E5%B8%B8%E8%AD%98-%E6%9C%89%E9%97%9C%E6%BB%BE%E5%8B%95%E7%9A%84%E9%A1%9E%E5%9E%8B-%E9%95%B7%E5%BE%97%E5%BE%88%E5%83%8F-，2013。
[2]Jammu, N. S., & Kankar, P. K. (2011). A review on prognosis of rolling element bearings. International Journal of Engineering Science and Technology, 3(10), 7497-7503.
[3]Yang, W., & Court, R. (2013). Experimental study on the optimum time for conducting bearing maintenance. Measurement, 46(8), 2781-2791.
[4]Ali, J. B., Fnaiech, N., Saidi, L., Chebel-Morello, B., & Fnaiech, F. (2015). Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals. Applied Acoustics, 89, 16-27.
[5]Zimroz, R., Bartelmus, W., Barszcz, T., & Urbanek, J. (2014). Diagnostics of bearings in presence of strong operating conditions non-stationarity—A procedure of load-dependent features processing with application to wind turbine bearings. Mechanical systems and signal processing, 46(1), 16-27.
[6]Pan, Y., Chen, J., & Guo, L. (2009). Robust bearing performance degradation assessment method based on improved wavelet packet–support vector data description. Mechanical Systems and Signal Processing, 23(3), 669-681.
[7]Samanta, B., & Al-Balushi, K. R. (2003). Artificial neural network based fault diagnostics of rolling element bearings using time-domain features. Mechanical systems and signal processing, 17(2), 317-328.
[8]Li, B., Chow, M. Y., Tipsuwan, Y., & Hung, J. C. (2000). Neural-network-based motor rolling bearing fault diagnosis. IEEE transactions on industrial electronics, 47(5), 1060-1069.
[9]Peter, W. T., Peng, Y. A., & Yam, R. (2001). Wavelet analysis and envelope detection for rolling element bearing fault diagnosis—their effectiveness and flexibilities. Journal of vibration and acoustics, 123(3), 303-310.
[10]FernáNdez-Francos, D., MartíNez-Rego, D., Fontenla-Romero, O., & Alonso-Betanzos, A. (2013). Automatic bearing fault diagnosis based on one-class ν-SVM. Computers & Industrial Engineering, 64(1), 357-365.
[11]Al-Raheem, K. F., & Abdul-Karem, W. (2010). Rolling bearing fault diagnostics using artificial neural networks based on Laplace wavelet analysis. International Journal of Engineering, Science and Technology, 2(6).
[12]林育新，滾動軸承智能診斷與剩餘壽命預估之研發，國立中正大學機械工程學系碩士論文，2017。
[13]江玟菱，進給系統健康診斷技術之研發，國立中正大學機械工程學系碩士論文，2018。
[14]Liu, F. T., Ting, K. M., & Zhou, Z. H. (2008, December). Isolation forest. In 2008 Eighth IEEE International Conference on Data Mining (pp. 413-422). IEEE.
[15]Isolation Forest example, https://scikit-learn.org/dev/auto_examples/ensemble/plot_isolation_forest.html#sphx-glr-auto-examples-ensemble-plot-isolation-forest-py, 2019.
[16]屈梁生，機械故障的全息診斷原理，科學出版社，2007。
[17]劉石與屈梁生，回轉機械故障診斷中的三維全息譜，西安交通大學學報，第38卷，第9期，2004。
[18]Chen, W. R., Yun, Y. H., Wen, M., Lu, H. M., Zhang, Z. M., & Liang, Y. Z. (2016). Representative subset selection and outlier detection via isolation forest. Analytical Methods, 8(39), 7225-7231.
[19]Anomaly Detection, https://www.slideshare.net/mlvlc/l14-anomaly-detection, 2015.
[20]Liu, F. T., Ting, K. M., & Zhou, Z. H. (2012). Isolation-based anomaly detection. ACM Transactions on Knowledge Discovery from Data (TKDD), 6(1), 3.
[21]Data Science Basics: An Introduction to Ensemble Learnings, https://thetazero.com/news/data-science-basics-an-introduction-to-ensemble-learners-ssp, 2016.
[22]Chen, P., Wang, K., & Feng, K. (2016, October). Application of order-tracking holospectrum to cracked rotor fault diagnostics under nonstationary conditions. In 2016 Prognostics and system health management conference (PHM-Chengdu) (pp. 1-6). IEEE.
[23]Acoustics and Vibration Database，http://data-acoustics.com/measurements/bearing-faults/bearing-6/, 2012.
[24]Nectoux, P., Gouriveau, R., Medjaher, K., Ramasso, E., Chebel-Morello, B., Zerhouni, N., & Varnier, C. (2012, June). PRONOSTIA: An experimental platform for bearings accelerated degradation tests. In IEEE International Conference on Prognostics and Health Management, PHM'12. (pp. 1-8). IEEE Catalog Number: CPF12PHM-CDR.
[25]SKF Static misalignment，https://www.skf.com/ph/products/bearings-units-housings/bearing-units/ball-bearing-units/principles/design-of-y-bearing-arrangements/misalignment/index.html.