節流器為液靜壓軸承系統中重要的關鍵零組件，其構型會影響整個液靜壓系統的剛性及承載能力。本研究著重於自補償式節流器應用於雙向墊液靜壓系統之情況，於理論方面，本文藉由自補償式節流器的運作原理與雙向墊液靜壓軸承的基本理論，推導出相關的物理理論模型，並進一步利用雙向墊液靜壓實驗平台，量測不同負載下其壓力、流量及油膜厚度之變化，進行理論與模擬之驗證。然而，雙向墊系統的理論模型為非線性，在進行理論模擬時需做許多假設條件，再加上實驗過程中誤差的影響，使得模擬結果與實際情況有所偏差。
為解決此一問題，本研究結合物理模型與機器學習中的多層感知器模型，建立一混合模型(Hybrid model)，並以實驗數據訓練該模型，透過深度學習讓該模型學習物理理論模型未包含的訊息以修正物理模型之誤差，讓預測結果更貼近實際狀況；此外由於結合物理模型之緣故，此一模型相較於單獨使用MLP模型，具有較佳的外推能力，故在探討規格品外之設計參數(如彈簧剛性或溝槽流阻)時，能夠提高不同設計參數下預測液靜壓軸承剛性表現之準確性，最終達到輔助最佳化節流器設計之目標。

The flow restrictor is a key component in the hydrostatic bearing, which configuration will affect the stiffness and load-carrying capacity of the hydrostatic bearing. Thus, the goal of this paper is to improve the stiffness of the hydrostatic opposed-pad system to a level of near infinite by optimizing the design parameters of the self-compensating restrictor. However, the design of a self-compensating restrictor is always a challenging subject because the theoretical model has been greatly simplified and the equations are coupled and non-linear.
This thesis proposes a hybrid model, which combines the theoretical model and multi-layer perceptron (MLP) model, to predict the stiffness of the hydrostatic opposed-pad system. Since the hybrid model contains the MLP model and theoretical model, it not only can deal with non-linear problems but also has good extrapolation ability. The training data are collected from a hydrostatic opposed-pad system experiment, which measures pressure, load, flow rate, and oil-film thickness. Based on training data, the hybrid model predicted results are closer to the actual situation.
By comparing the MLP model with the hybrid model predicted results, the hybrid model has better accuracy of the prediction results and extrapolation ability, so it can optimize the design parameters of self-compensating restrictor to improve the stiffness of hydrostatic bearings.

摘要-----------------------------------I
Abstract-----------------------------------II
誌謝-----------------------------------III
目錄-----------------------------------IV
圖目錄-----------------------------------VII
表目錄-----------------------------------XI
符號表-----------------------------------XII
第一章 導論-----------------------------------1
1-1 研究背景-----------------------------------1
1-2 液靜壓軸承與節流器文獻回顧------------------------3
1-2-1 固定式節流器之研究-----------------------------3
1-2-2 主動式節流器之研究-----------------------------4
1-2-3 複合式節流器之研究-----------------------------5
1-3 類神經網路文獻回顧-------------------------------7
1-3-1 人工智慧發展回顧-------------------------------7
1-3-2 類神經網路應用於工程領域-----------------------9
1-4 研究動機與研究架構----------------------------11
第二章 液靜壓軸承與節流器基本理論推導--------------13
2-1 油墊封油面流阻計算----------------------------13
2-1-1 方形封油面流場分析--------------------------14
2-1-2 圓形封油面流場分析--------------------------16
2-1-3 方形與圓形封油面流阻公式整理-----------------19
2-2 溝槽式節流器---------------------------------20
2-3 自補償式節流器--------------------------------23
第三章 液靜壓軸承雙向墊流阻網路法分析---------------25
3-1 雙向墊流阻網路法分析---------------------------25
3-1-1 溝槽式節流器搭配雙向墊系統-------------------28
3-1-2 自補償式節流器搭配雙向墊系統-----------------29
3-1-3 上節流器為自補償式與下節流器為溝槽式----------34
3-1-4 上節流器為溝槽式與下節流器為自補償式----------36
第四章 節流器實驗研究------------------------------39
4-1 實驗架設與設備---------------------------------39
4-1-1 液靜壓供油系統與冷卻系統----------------------40
4-1-2 液靜壓軸承實驗平台系統------------------------41
4-1-3 實驗量測設備---------------------------------43
4-1-4 實驗架設---------------------------------46
4-2 上、下節流器皆為自補償式節流器之實驗研究------47
4-2-1 實驗步驟---------------------------------47
4-2-2 更換上節流器設計參數之實驗結果分析---------49
4-2-3 更換下節流器設計參數之實驗結果分析----------55
4-3 自補償式與溝槽式節流器實驗研究---------------61
4-3-1 實驗步驟---------------------------------61
4-3-2 上節流器搭配自補償式下節流器搭配溝槽式實驗結果分析----63
4-3-3 上節流器搭配溝槽式下節流器搭配自補償式實驗結果分析----65
4-4 自補償式節流器搭配雙向墊與單向墊之結果比較------------------66
第五章 機器學習之混合模型---------------------------------69
5-1 機器學習模型---------------------------------70
5-1-1 機器學習---------------------------------70
5-1-2 多層感知器網路簡介---------------------------------71
5-1-3 多層感知器網路訓練原理---------------------------------75
5-1-4 混合模型簡介---------------------------------79
5-2 多層感知器模型建立---------------------------------82
5-2-1 資料前處理---------------------------------82
5-2-2 多層感知器網路結構---------------------------------83
5-2-3 網路驗證---------------------------------85
5-3 混合模型預測結果探討---------------------------------87
第六章 結論與未來工作---------------------------------97
6-1 結論---------------------------------97
6-2 未來工作---------------------------------98
參考文獻---------------------------------100

[1] Girard, L. D., 1862, Application des Surfaces Glissantes, Paris, Bachelier
[2] Slocum, A. H., 1992, Precision Machine Design, NJ, Englewood Cliffs:Prentice Hall
[3] 黃華志，2009， “液靜壓軸承技術清大演講”，工研院機械所.
[4] Telingater, V. S., 1972, “Hydrostatic Slideways Using Standard Bearings ”, Machines and Tooling, Vol. 43, Iss. 2, pp.15-20
[5] Raimondi, A. A., Boyd, J.,1957, “An Analysis of Orifice and Capillary-compensated Hydrostatic Journal Bearing ” , Lubr. Eng, Vol. 13, Iss. 1, pp.28-37
[6] Ling, T. S., 1962, “On the Optimization of the Stiffness of Externally Pressurized Bearings”, Trans. ASME. J. Basic Eng, Vol. 84, pp.119-122
[7] O’Donoghue, J. P., 1972, “Parallel Orifice and Capillary Control for Hydrostatic Journal bearings”, Tribology International, Vol. 5, pp.81-82
[8] Sharma, S. C., Sinhasan, R., Jain, S. C., Singh, N., and Singh, S. K., 1995, “Comparative study of the performance of six-pocket and four-pocket hydrostatic/hybrid flexible journal bearings”, Tribology Transactions, Vol. 28, pp.531-539
[9] Sharma, S. C., Sinhasan, R., Jain, S. C., Singh, N., and Singh, S. K., 1998, “Performance of Hydrostatic/Hybrid Journal Bearings with Unconventional Recess Geometries”, Tribology Transactions, Vol. 41, pp.375-381
[10] Mohsin, M. E., 1963, “The Use of Controlled Restrictors for Compensating Hydrostatic Bearing”, Third International Conference on Machine Tool Design Research, pp.129-424
[11] Rowe, W. B. and O’Donoghue, J.P., 1970, “Diaphragm Valves for Controlling Opposed Pad Hydrostatic Bearing”, Proc. I. E. Tribology, Vol. 184, pp.1-9
[12] Moris, S. A., 1972, “Passively and Actively Controlled Externally Pressurized Oil-film Bearing”, Trans. ASME. Ser. F, Vol. 94, pp.56-63
[13] Rowe W. B., 1976, Hydrostatic Bearing Patent Application no.51919/67. Publish 15th November170 (1):602. Assigned to Wickman Ltd
[14] Rowe W. B., 1969, Hydrostatic bearing patent application no.22072/66. Publish 15th November 170 (1):602. Assigned to Wickman Ltd
[15] Tully, N., 1977, “Static and Dynamic Performance of an Infinite Stiffness Hydrostatic Thrust Bearing”, Trans. of ASME. J. of Lubrication Tech, Vol. 99, Iss.1, pp.106-112
[16] Osumi T., Mori H., Ikeuchi K., 1985, “Effects of Stabilizer on Initial Response of Self Controlled Externally Pressurized Bearings”, Trans. JSLE, Vol. 20, pp.651-657
[17] Yoshimoto, S., Anno, Y., Amari K., 1990, “Static Characteristics of Hydrostatic Journal Bearing with a Self Controlled Restrictor Employing Floating Disk”, Trans. JSLE, Vol. 56, pp.3360-3367
[18] Yoshimoto S., Kikuchi K., 1999, “Step Response Characteristics of Hydrostatic Journal Bearings with Self-controlled Restrictor Employing Floating Disk”, Trans. Int, Vol. 121, Iss. 4, pp. 315-320
[19] Robert Schoenfold, 2001, Regulator for Adjusting the Fluid Flow in a Hydrostatic or Aerostatic Device. US Patent number 6276491B1
[20] Singh, N., Sharma, S. C.,Jain, S. C., and Reddy, S. S., 2004, “Performance of Membrane Compensated Multirecess Hydrostatic Hybrid Flexible Journal Bearing System Considering Various Recess Shapes ”, Tribology International,Vol. 37, pp.11-24
[21] Kang, Y., Shen, P. C., Chen, C. H., Chang Y. P. and Lee, H. H., 2007, “Modified determination of fluid resistance for membrane-type restrictors”, Industrial Lubrication and Tribology, pp.123-131
[22] Mayer, J. E. and Shaw, M. C., 1963, “Characteristics of Externally Pressurized Bearing Having Variable External Flow Restrictors”, ASEM Journal of Basic Engineering, Vol. 85, pp.291
[23] Schoenfold, R., Flow-rate regulator for liquid and/or gaseous materials. D.E. Patent No. 3150117 A1 (1983)
[24] 王翊丞，2015，“液靜壓軸承複合型節流裝置設計與實驗”國立清華大學動力機械系碩士論文
[25] 宋震國、王翊丞，2015，“主動式補償液靜壓軸承及其節流器”，中華民國發明專利第I597435號
[26] 黃裕修，2020，“以多層感知類神經網路輔助複合式節流器設計”國立清華大學動力機械系碩士論文
[27] McCulloch, W.S. & Pitts, W., 1943, “A logical calculus of the ideas immanent in nervous activity”, Bulletin of Mathematical Biophysics, Vol. 5, pp.115-133
[28] Hebb, D.O., 1949, The Organization of Behavior, New York, Wiley
[29] 丁川康，2020，人工智慧導論Lec.1 Introduction to Artificial Intelligence課程講義
[30] Rosenblatt, F., 1957, The perceptron: a perceiving and recognizing automaton, Report 85-460-1, Cornell Aeronautical Laboratory
[31] Minsky, M., Papert, S., 1969, Perceptrons: An Introduction to Computational Geometry, Cambridge, MA, USA: MIT Press.
[32] Hopfield, J. J., April 1982, “Neural networks and physical systems with emergent collective computational abilities”, Proceedings of the National Academy of Sciences of the USA, vol. 79, Iss. 8, pp. 2554–2558
[33] Rumelhart, D. E., Hinton, G.E., Williams, R.J., 1986, “Learning representations by back-propagating errors”, Nature, Vol. 323, pp. 533-536
[34] Hinton, G. E., Sejnowski, T. J., Ackley, D. H., 1985, “A learning algorithm for boltzmann machines”, Cognitive Science, Vol. 9, pp. 147-169
[35] Hinton, G. E. and Salakhutdinov, R. R., 2006, “Reducing the Dimensionality of Data with Neural Networks”, Science, Vol. 313, Iss. 5786, pp. 504-507
[36] 張斐章，張麗秋，2010，類神經網路導論：原理與應用，滄海書局
[37] Canbulut, F., Sinanoglu, C., Yildirim, S., 2004, “Analysis of Effects of Sizes of Orifice and Pockets on the Rigidity of Hydrostatic Bearing Using Neural Network Predictor System”, KSME International Journal, Vol. 18, Iss. 3, pp. 432 ~ 442
[38] Canbulut, F., Sinanoglu, C., 2004, “ An investigation on the performance of hydrostatic pumps using artificial neural network”, JSME International Journal, Vol. 47, Iss. 3, pp 864-872
[39] Canbulut, F., 2004, “The experimental analyses of effects of the geometric and working parameters on the circular hydrostatic thrust bearing”, JSME International Journal, Vol. 48, Iss. 4, pp 715-722
[40] Canbulut, F., Yildirim, S., and Sinanoglu, C., 2004, “Design of an artificial neural network for analysis of frictional power loss of hydrostatic slipper bearings”, Tribology Letters, Vol. 17, Iss. 4, pp 887-898
[41] Bhutani N., Rangaiah G. P., Ray A. K., 2006,“First-Principles, Data-Based, and Hybrid Modeling and Optimization of an Industrial Hydrocracking Unit”, Industrial & Engineering Chemistry Research, Vol. 45, pp. 7807-7816.
[42] Rafieea, J., Arvania, F., Harifib, A., Sadeghic, M.H., 2007, “Intelligent condition monitoring of a gearbox using artificial neural network”, Mechanical Systems and Signal Processing, Vol. 21, pp 1746–1754
[43] Saxena, A., Saad, A., 2007, “Evolving an artificial neural network classifier for condition monitoring of rotating mechanical systems”, Applied Soft Computing, Vol. 7, pp 441–454.
[44] Wang, Y., Liu, Z., Zhao, Y., Chen, Q., Cai, L., 2019, “Research on an ANN system for monitoring hydrostatic turntable performance based on ODNE training”, Tribology International, Vol. 133, pp.21-31.
[45] Timur Bikmukhametov, Johannes Jäschke, 2020, “Combining machine learning and process engineering physics towards enhanced accuracy and explainability of data-driven models”, Computers and Chemical Engineering, Vol. 133, pp.106834
[46] 高惟禎，2019，“以多層感知器網路輔助液靜壓軸承節流器設計” 國立清華大學動力機械系碩士論文
[47] Bruus, H., 2008, Theoretical microfluidics. Oxford master series in condensed matter physics, Oxford University Press
[48] 鍾洪，張冠坤，2007，液體靜壓動靜壓軸承設計使用手冊，電子工業出版社：p.30
[49] 李威志，2012，“新型主動式補償液靜壓軸承之靜動態特性分析”國立清華大學動力機械系碩士論文
[50] 鮑思丞，2016，“智慧型線性液靜壓滑塊模組設計”國立清華大學動力機械系碩士論文
[51] 程瑾文，2017，“泛用型虛實整合系統架構建立─以液靜壓節流器之調整為驗證載具”國立清華大學動力機械系碩士論文
[52] 張軼峯，2018，“液靜壓複合式節流器設計─輔以類神經網路之決策” 國立清華大學動力機械系碩士論文
[53] 丁川康，2020，人工智慧導論Lec.18.7 Neural Networks課程講義
[54] 李宏毅，機器學習課程講議。
檢自：http://speech.ee.ntu.edu.tw/~tlkagk/courses_ML17_2.html
[55] Standford CS class, CS231n: Convolutional Neural Networks for Visual Recognition.
檢自：http://cs231n.github.io/neural-networks-3/
[56] 丁川康，2020，人工智慧導論Lec.18 Learning from Observation課程講義