本研究所設計之主軸專為微型軸承與小徑軸承量測應用，透過振動感知器監控軸
承運行情況。測試過程中將待測軸承安裝於主軸軸心並施加適當推力載荷，以獲取軸
承運轉時之振動數據。該主軸結構類似軸頸軸承，並搭配Turbine Oil No.56 作為潤滑
介質。隨著運行時間增加，軸心、銅襯間之磨耗將導致振動值上升，進而影響量測準
確性。
本研究提出三種建模策略以預測主軸振動值並進行良品與不良品判別。方法一以
振動值反向預測配合間隙，因特徵過於單一，模型表現不佳，測試 R2 多為負值。方
法二改以幾何尺寸與表面粗糙度等數值特徵預測振動值，表現顯著提升，MLP 模型測
試 R2 可達 0.493。方法三進一步結合 ResNet101 擷取之圖像特徵與數值資料，建構
多模態模型，整體表現穩定，但高維特徵導致部分模型產生過擬合，第一層預測趨於
一致，限制堆疊效果。進一步將圖像特徵降維後，雖抑制過擬合，但預測能力同步下
降。
分類方面，模型多能穩定辨識良品，但不良品 Recall 偏低，受限於樣本不平衡與
邊界樣本比例過高。整體而言，融合圖像與數值特徵有助提升振動預測能力，未來可
從特徵選擇、資料擴增與不平衡學習進行優化，以強化缺陷辨識與實務應用效能。

The spindle developed in this study is designed for measuring miniature and smalldiameter
bearings. A vibration sensor monitors the bearing’s condition during testing, where
the bearing is mounted on the spindle shaft under thrust load to collect vibration data. The
spindle resembles a journal bearing and uses Turbine Oil No.56 for lubrication. Over time,
wear between the shaft and copper bushing increases vibration, affecting measurement
accuracy.
Three modeling strategies are proposed to predict spindle vibration and classify product
quality. Method 1 uses vibration to inversely predict clearance but performs poorly due to
limited input features, yielding mostly negative test R2 values. Method 2 predicts vibration
using numerical features like geometry and surface roughness, showing notable improvement
with MLP reaching a test R2 of 0.493. Method 3 combines ResNet101-extracted image
features with numerical data to build a multimodal model. Performance remains stable,
though high-dimensional features lead to overfitting and similar outputs from first-layer
models, limiting stacking effectiveness. Dimensionality reduction mitigates overfitting but
reduces predictive power.
For classification, models reliably identify good samples, but defective recall remains
low due to data imbalance and borderline cases. Overall, combining image and numeric
features improves vibration prediction. Future work may enhance defect detection through
feature selection, data augmentation, and imbalanced learning.

﹝1﹞ M. Moschopoulos, G. N. Rossopoulos, and C. I. Papadopoulos, “Journal
bearing performance prediction using machine learning and octave-band signal analysis
of sound and vibration measurements,” POLISH MARITIME RESEARCH, vol. 28, no.
3(111), pp. 137–149, Polish Maritime University, 2021.
﹝2﹞ W.-J. Lin, S.-H. Lo, H.-T. Young, and C.-L. Hung, “Evaluation of deep
learning neural networks for surface roughness prediction using vibration signal
analysis,” Applied Sciences, vol. 9, no. 7, article 1462, MDPI, Apr. 2019.
﹝3﹞ N. Motamedi, V. Magnier, and H. Wannous, “Towards the identification
of the link between the contact roughness and the friction-induced vibration: Use of deep
learning,” European Journal of Mechanics - A/Solids, vol. 94, pp. 1–19, Elsevier, 2023.
﹝4﹞ G.-C. Lee, Y.-C. Lin, and C.-L. Hung, “Application of Vibration Signal
Analysis for Evaluating Surface Roughness in Milling Operation,” Applied Sciences,
vol. 8, no. 10, article 1859, MDPI, Oct. 2018.
﹝5﹞ L. Zoupas, M. Wodtke, C. I. Papadopoulos, and M. Wasilczuk, “Effect of
manufacturing errors of the pad sliding surface on the performance of the hydrodynamic
thrust bearing,” Tribology International, vol. 134, pp. 211–220, Elsevier, Jan. 2019.
﹝6﹞ S. Zhang, S. Zhang, B. Wang, and T. G. Habetler, “Deep learning
algorithms for bearing fault diagnostics: A comprehensive review,” IEEE Access, vol. 8,
pp. 29857–29881, IEEE, 2020.
﹝7﹞ T. Nagaraju, S. C. Sharma, and S. C. Jain, “Influence of surface roughness
effects on the performance of non-recessed hybrid journal bearings,” Tribology
International, vol. 35, no. 7, pp. 467–487, Elsevier, July 2002.
﹝8﹞ J. W. Lund, “Review of the concept of dynamic coefficients for fluid film
journal bearings,” Journal of Tribology, vol. 109, no. 1, pp. 37–41, ASME, Jan. 1987.
﹝9﹞ A. Liaw and M. Wiener, “Classification and regression by randomForest,”
R News, vol. 2, no. 3, pp. 18–22, December 2002.
﹝10﹞ A. F. Quiñonez and G. E. Morales-Espejel, “Surface roughness effects in
hydrodynamic bearings,” Tribology International, vol. 98, pp. 212–219, Elsevier, June
2016.
﹝11﹞ V. Salunkhe and R. Desavale, “An intelligent prediction for detecting
bearing vibration characteristics using a machine learning model,” Journal of
Nondestructive Evaluation, Diagnostics and Prognostics of Engineering Systems, vol. 4,
no. 3, pp. 1–20, ASME, Jan. 2021.
﹝12﹞ C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning,
vol. 20, no. 3, pp. 273–297, Springer, Sept. 1995.
﹝13﹞ C. J. C. Burges, “A tutorial on support vector machines for pattern
recognition,” Data Mining and Knowledge Discovery, vol. 2, no. 2, pp. 121–167, Kluwer
Academic Publishers, 1998.
﹝14﹞ R. S. Umamaheswara Raju, K. Ravi Kumar, K. Vargish, and M. Bharath
Kumar, “Machine learning based surface roughness assessment via CNC spindle bearing
vibration,” International Journal on Interactive Design and Manufacturing (IJIDeM), vol.
19, pp. 477–494, Springer, 2025.
﹝15﹞ A. Sharma, L. Mathew, R. Jigyasu, and S. Chatterji, “Bearing fault
diagnosis using weighted K-nearest neighbor,” Proceedings of the 2nd International
Conference on Trends in Electronics and Informatics (ICOEI 2018), IEEE, pp. 1132–
1137, June 2018.
﹝16﹞ M. Amarnath, V. Sugumaran, and H. Kumar, “Exploiting sound signals
for fault diagnosis of bearings using decision tree,” Measurement, vol. 46, no. 3, pp.
1250–1256, Elsevier, April 2013.
﹝17﹞ V. Sugumaran, V. Muralidharan, and K. I. Ramachandran, “Feature
selection using Decision Tree and classification through Proximal Support Vector
Machine for fault diagnostics of roller bearing,” Mechanical Systems and Signal
Processing, vol. 21, no. 2, pp. 930–942, Elsevier, February 2007.
﹝18﹞ C. Sun, Z. Zhang, and Z. He, “Research on bearing life prediction based
on support vector machine and its application,” Journal of Physics: Conference Series,
vol. 305, pp. 012028, IOP Publishing, July 2011.
﹝19﹞ F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O.
Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D.
Cournapeau, M. Brucher, M. Perrot, and É. Duchesnay, “Scikit-learn: Machine learning
in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, October
2011.
﹝20﹞ 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, Hindawi, January 2013.
﹝21﹞ A. Moosavian, H. Ahmadi, A. Tabatabaeefar, and B. Sakhaei, “An
appropriate procedure for detection of journal-bearing fault using power spectral density,
K-nearest neighbor and support vector machine,” International Journal on Smart Sensing
and Intelligent Systems, vol. 5, no. 3, pp. 685–700, September 2012.
﹝22﹞ K. M. Saridakis, P. G. Nikolakopoulos, C. A. Papadopoulos, and A. J.
Dentsoras, “Identification of wear and misalignment on journal bearings using artificial
neural networks,” Proceedings of the Institution of Mechanical Engineers, Part J: Journal
of Engineering Tribology, vol. 226, no. 1, pp. 46–56, SAGE Publications, January 2012.
﹝23﹞ J. Moder, P. Bergmann, and F. Grün, “Lubrication regime classification of
hydrodynamic journal bearings by machine learning using torque data,” Lubricants, vol.
6, no. 4, article 108, MDPI, December 2018.
﹝24﹞ D. Dowson, “A generalized Reynolds equation for fluid-film lubrication,”
International Journal of Mechanical Sciences, vol. 4, no. 2, pp. 159–170, Elsevier,
March–April 1962.
﹝25﹞ T. Narendiranath Babu, T. Manvel Raj, and T. Lakshmanan, “A review on
application of dynamic parameters of journal bearing for vibration and condition
monitoring,” Journal of Mechanics, vol. 31, no. 4, pp. 391–416, The Society of
Theoretical and Applied Mechanics, August 2015.
﹝26﹞ T. Abedin, S. P. Koh, C. T. Yaw, C. C. Phing, S. K. Tiong, J. D. Tan, K.
Ali, K. Kadirgama, and F. Benedict, “Vibration signal for bearing fault detection using
Random Forest,” Journal of Physics: Conference Series, vol. 2467, pp. 012017, IOP
Publishing, December 2022.
﹝27﹞ K. F. Brethee, J. Ma, G. R. Ibrahim, F. Gu, and A. D. Ball, “Vibration
analysis for diagnosis of tribo-dynamic interaction in journal bearings,” in Proceedings
of the International Conference on the Efficiency and Performance Engineering Network
(TEPEN 2022), Mechanisms and Machine Science, vol. 129, pp. 877–888, Springer,
March 2023.
﹝28﹞ M. Pusterhofer, F. Summer, M. Maier, and F. Grün, “Assessment of Shaft
Surface Structures on the Tribological Behavior of Journal Bearings by Physical and
Virtual Simulation,” Lubricants, vol. 8, no. 1, pp. 1–16, MDPI, January 2020.
﹝29﹞ L. Mason, J. Baxter, P. Bartlett, and M. Frean, “Boosting algorithms as
gradient descent,” in Advances in Neural Information Processing Systems (NeurIPS 12),
Denver, CO, USA, Nov. 29–Dec. 4, 1999.