軸承在所有機械設備中，是最重要的機械部件之一，而軸承運行時之健 康狀況，除了直接影響整台設備的機能性，亦係造成設備故障的主要因素; 因此，對於設備診斷、維護時能夠精確評估軸承的健康狀況極為重要。
傳統軸承故障診斷方式仍存在許多改進空間，例如:僅限於同轉速下才 可進行軸承故障診斷，為解決此問題，本研究針對高低不同轉速之軸承設計 軸承故障診斷系統。該系統以卷積神經網路為基礎，將不同轉速之資料作為 資料集以建置神經網路模型，透過深度學習神經網路實現一跨轉速之軸承故 障診斷系統，為證明該方法的可信度，本研究資料來自具公信力的 Case WesternReserve 大學軸承資料中心，該資料中心網站有提供之軸承振動故障 訊號，且利用該網站提供的軸承訊號驗證本研究提出的方法，證實本研究之 故障診斷系統功效卓越。
本研究達成高低不同轉速之軸承資料進行同時分類，及利用神經網路模 型，成功分類未參與建模的轉速資料，且正確率高達 99.66%。

Bearings are among the most important mechanical components in all mechanical equipment. The health status of the bearings, in addition to directly affecting the functionality of the entire equipment, is also the main cause of equipment failure; therefore, how accurate the assessment is The health of the bearing is very important.
There are some problems in the traditional bearing fault diagnosis, including bearing fault diagnosis only at the same speed, in order to solve the appeal problem; therefore, this study will design a bearing fault diagnosis system for bearings with different speeds. The system uses a convolutional neural network. Based on this, a neural network model with different height and rotation speeds was constructed and a bearing fault diagnosis system with a span speed was built through a deep learning neural network. To demonstrate the credibility of the method, a case with credibility was used in this study. Western Reserve University Bearing Information Center, the data center site has provided a bearing vibration fault signal, and use the bearing signal provided by the site to verify the method proposed in this study, experiments have proved that this method is effective.
In the article's experimental results, the study achieved simultaneous classification of bearing data with different high and low speeds, and the use of the network neural network model to successfully classify the speed data not involved in the modeling, and the correct rate of up to 99.66%.

一、中文文獻
科言君, "CNN(卷積神經網絡)、RNN(循環神經網絡)、DNN(深度神經 網絡)的內部網絡結構有什麼區別," 知乎, 2016, Available: https://www.zhihu.com/question/34681168
孫驍, "零相移濾波器原理," Available:https://wenku.baidu.com/view/5d27e80af78a6529647d53d8.html

二、英文文獻
F. Hashim, “Bearing failure led to Jetstar A320 engine power loss,” FlightGlobal, 2017, Available:https://www.flightglobal.com/news/articles/ bearing-failure-led-to-jetstar-a320-engine-power-los-436621/.
S. Collie, "Arteon recalled 64 cars affected by wheel-bearing fault," Caradvice, 2017, Available:http://www.caradvice.com.au/604591/2018- golf-passat-and-arteon-recalled-for-wheel-bearing-housing-fix/.
Andrew K.S. Jardine, D. Lin and D. Banjevic, "A review on machinery diagnostics and prognostics implementing condition-based maintenance," Mechanical Systems and Signal Processing, vol. 20, no. 7, pp. 1483-1510, 2005.
[4] S. D. Wu, P. H. Wu, C. W. Wu, J. J. Ding, and C. C. Wang, "Bearing Fault Diagnosis Based on Multiscale Permutation Entropy and Support Vector Machine," Entropy, vol. 14, no. 8, pp. 1343-1356, 2012.
Case Western Reserve University Bearing Data Center, Available: http://csegroups.case.edu/bearing datacenter/pages/download-data-file.
[Tensorflow, 官方網站, Available: https://www.tensorflow.org/.
J. Shi, X. Wu, J. Zhou and S. Wang, "BP neural network based bearing fault diagnosis with differential evolution & EEMD denoise," 2017 9th International Conference on Modelling, Identification and Control(ICMIC), pp. 1038-1043, Kunming, 2017.
H. Yuan, X. Hou and H. Wang, "Multi-fault diagnosis for rolling bearing based on double parallel extreme learning machine & kurtosis spectral entropy," 2017 9th International Conference on Modelling, Identification and Control (ICMIC), pp. 758-763, Kunming, 2017.
P. J. Werbos, "Beyond regression: new tools for prediction and analysis in the behavioral science," Ph. D. Thesis, Harvard University, 1974.
Wikipedia contributors. "Overfitting," Wikipedia, The Free Encyclopedia, 2018.
Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436-444, 2015.
D. Silver, et al, "Mastering the game of go with deep neural networks and tree search," Nature, vol. 29, no. 7587, pp. 484–489, 2016.
S. S. Farfade, M. Saberian, L. J. Li, "Multi-view Face Detection Using Deep Convolutional Neural Networks," Proceedings of the 5th ACM on International Conference on Multimedia Retrieval(ICMR), pp. 643-650, Shanghai, China, Jun. 23 - 26, 2015.
A. Krizhevsky, I. Sutskever, and G. Hinton, "ImageNet classification with deep convolutional neural networks." In Advances in Neural Information Processing Systems 25, pp. 1106–1114, 2012.
K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition,"International Conference on Learning Representations 2015, San Diego, CA, May 7-9, 2015.
Christian Szegedy, Wei Liu, et al, "Going deeper with convolutions," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1 - 9, 2015.
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, "Deep Residual Learning for Image Recognition," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770 - 778, 2016.
Aaron M. Bornstein, "Is Artificial Intelligence Permanently Inscrutable?," http://nautil.us/issue/40/learning/is-artificial-intelligence-permanently- inscr utable
P. J. Werbos, "Beyond regression: new tools for prediction and analysis in the behavioral science," Ph. D. Thesis, Harvard University, 1974.
R. Raina, A. Madhavan, and A. Y. Ng, "Large-scale deep unsupervised learning using graphics processors," in Proceedings of the 26th Annual International Conference on Machine Learning, 2009, pp. 873-880: ACM.
Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278 - 2324, 1998.
M. D. Zeiler and R. Fergus, "Visualizing and understanding convolutional networks," In Proc. ECCV, pp 818-833, 2014.
J. Donahue, Y. Jia, O. Vinyals, J. Hoffman, N. Zhang, E. Tzeng, and T. Darrell, "DeCAF: a deep convolutional activation feature for generic visual recognition," In: ICML., pp. 647-655, 2014.
N. Srivastava, et al, "Dropout: A simple way to prevent neural networks from overfitting," The Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929-1958, 2014.
Wikipedia contributors, "Aliasing," Wikipedia, The Free Encyclopedia, 2018.
F. Gustafsson, "Determining the initial states in forward-backward filtering," IEEE Transactions on Signal Processing, vol. 44, no. 4, pp. 988- 992, 1996.
Keskar, Nitish Shirish, et al. "On large-batch training for deep learning: Generalization gap and sharp minima," 5th International Conference on Learning Representations(ICLR), Toulon, France, 2017.