臺灣博碩士論文加值系統

在本論文中，考慮剛性不同的接觸線所產生的不確定性，這些不確定性會影響集電弓的電流蒐集穩定度，因此將針對弓網系統進行研究，以改善鐵路電車電力的供應。為了實現穩定的電流收集，從而提高了整體的電力供應，提出了模糊BP演算法和自適應模糊滑模控制方案。首先，利用滑模控制（SMC）實現至具強健性的集電弓與接觸線系統的接觸力控制。然後，通過結合模糊神經網絡（FNN）與滑模控制來衰減傳統滑模控制造成的抖動問題。根據Lyapunov穩定性定理，主動控制和用於FNNS的自由參數自適應律可以得出有效抑制集電弓系統的振動。大量的模擬和比較結果表明，該自適應模糊滑模控制器不僅能保持漸近穩定，也可以大大改善電力傳輸的質量。此外，也比較了模糊BP算法和自適應模糊SMC之間的控制差異。

In this paper, the uncertain dynamic active pantograph-catenary system which considers the effect of different stiffness resulting from the uneven overhead wire is investigated to improve current collection for tram-train. In order to achieve stable current collection, and hence improve the performance of the overall electricity supply, Fuzzy BP algorithm and adaptive fuzzy sliding mode control scheme are proposed. First, sliding mode control (SMC) is introduced to implement the robust of contact force of pantograph-catenary system. Then, the uplift force which is applied to pantograph frame by actuator is constructed by incorporating fuzzy neural network (FNN) and sliding mode control to attenuate the chattering problem resulting from the sliding mode control. Based on the Lyapunov stability theorem, the active control law and adaptive laws for the free parameters of the FNNs can be derived to effectively suppress vibration of the pantograph system. Extensive simulations and comparisons show that the proposed adaptive fuzzy sliding controller not only can preserve the asymptotical stability but also can therefore greatly ameliorate the quality of electricity transfer. Furthermore, the comparative study between Fuzzy BP algorithm and adaptive fuzzy SMC is made.

第一章 緒論 1
1.1 研究動機與目的 1
1.2 文獻研討 2
1.3 論文架構 3
第二章 鐵路系統之集電弓描述 4
2.1鐵路系統簡介 4
表2.1 台灣目前使用之鐵路系統簡單比較 4
2.2集電弓架構 4
2.3集電弓動作原理 6
2.4弓網動力學 10
2.5集電弓數學模型分析 12
第三章 模糊邏輯系統理論 15
3.1 模糊邏輯系統簡介 15
3.2 模糊邏輯系統 16
3.3 模糊類神經網路 18
第四章 倒傳遞演算法控制 21
4.1倒傳遞演算法簡介 21
4.2倒傳遞演算法之模糊追蹤控制架構 21
4.3集電弓系統的BP演算法之識別器與控制器設計 24
4.4 BP演算法之模擬結果分析 28
表4.1 集電弓之系統參數 29
表4.2 模糊邏輯識別器的模糊歸屬函數初始值 30
表4.3 模糊邏輯控制器的模糊歸屬函數初始值 30
表4.4 倒傳遞演算法振動幅度比較 38
表4.5 不同振動條件之振幅抑制效果 39
第五章 適應性滑模控制 40
5.1適應性滑模控制簡介 40
5.2集電弓系統的適應性模糊滑模控制設計 41
5.3 適應性模糊滑模控制之模擬結果分析 45
表5.1適應性滑模控制振動幅度比較 53
表5.2 適應性滑模控制不同振動條件之振幅抑制效果 53
第六章 第二型模糊邏輯系統理論 54
6.1第二型模糊邏輯之目的 54
表6.1速度感受強度之高斯函數整理 55
6.2第二型模糊邏輯系統 56
第七章 倒傳遞第二型模糊演算法控制 60
7.1集電弓系統的BP模糊第二型演算法之識別器與控制器設計 60
7.2 BP第二型模糊演算法之模擬結果分析 68
表7.1 第二型模糊邏輯識別器的模糊歸屬函數初始值 68
表7.2 第二型模糊邏輯控制器的模糊歸屬函數初始值 69
第八章 適應性第二型模糊滑模控制 76
8.1集電弓系統的適應性第二型模糊滑模控制之控制器設計 76
8.2 適應性第二型模糊滑模控制之模擬結果分析 80
第九章 結論 85
9.1模擬結果總結 85
9.2未來工作 85
參考文獻………. 86

[1]A. P., E. U., “Contact force estimation and regulation in active pantographs: An algebraic observability approach”, IEEE Decision and Control, pp. 4341 – 4346, 2007.
[2]A. L.; A. P.; E. U., “Output-feedback control of the contact-force in high-speed-train pantographs”, Proceedings of the 40th IEEE Decision and Control, Vol.:2, pp. 1831 – 1836, 2001.
[3]S. Y.; Li C.; F. L., “Model-independent solution for active contact force control of pantographs in high-speed trains”, Chinese Control Conference (CCC), pp. 7250 – 7255, 2012.
[4]H. W.; Z. L.; Y. S.; X. L.; Z. H.; J. Z.; Y. W., “Detection of Contact Wire Irregularities Using a Quadratic Time–Frequency Representation of the Pantograph–Catenary Contact Force”, IEEE Transactions on Instrumentation and Measurement, Vol.:6, pp. 1385 – 1397, 2016.
[5]R. S.; M. C.; T. M., “Chaos theory based control of contact force in electric railway transportation system”, Environment and Electrical Engineering (EEEIC) , pp. 995 – 999, 2012.
[6]A. C. S.; F. M.; K. H. Z., “Neural-Network-Based Contact Force Observers for Haptic Applications”, IEEE Transactions on Robotics, Vol.: 22, pp. 1163 – 1175, 2006.
[7]H. J.; J. L.; H. L.; Z. H., “An extremum seeking based control strategy for pantograph-catenary contact force of high-speed trains”, IEEE Energy Conversion Congress and Exposition (ECCE), pp. 1333 – 1337, 2015.
[8]S. Y.; L. C.; F. L., “Model-independent solution for active contact force control of pantographs in high-speed trains”, Chinese Control Conference (CCC), pp. 7250-7255, 2012.
[9]J. L. W.; Z. P.; K.Y. Q., “Design of two-fuzzy neural-network controller for nonlinear systems”, Machine Learning and Cybernetics, Vol.:2, pp. 1141 – 1146, 2003.
[10]H. X.; C. S.; W. X., “Variable Structure Control Based on the Fuzzy Neural Networks”, NAFIPS Annual Meeting of the North American Fuzzy Information Processing Society, pp. 206 – 210, 2006.
[11]F. Y. Y.; S. Y. J., “The Research of Nonlinear Control Based on Fuzzy Neural Network”, Electrical and Control Engineering (ICECE), pp. 2417-2420, 2010.
[12]X. D.; H. S., “Estimation of project costs based on fuzzy neural network”, World of Information and Communication Technologies (WICT), pp. 1177-1181, 2012.
[13]J. M.; D. W., “Interval Type2 Fuzzy Sets”, Perceptual Computing:Aiding People in Making Subjective Judgments, pp. 35-63, 2010.
[14]F. G.; P. M.; F. V.; O. C., “Back propagation learning method with interval type-2 fuzzy weights in neural networks”, Neural Networks (IJCNN), pp. 1-6, 2013.
[15]M. R.; T. C. L.; B. R. S.; M. C. C., “Synchronization of two different chaotic systems using chattering-free adaptive interval type-2 fuzzy sliding mode control”, IEEE Conference on Industrial Electronics and Applications, pp. 121-126, 2010.
[16]S. K.; H. H.; G. O.; S. S., “A type2 Fuzzy Logic System for workforce management in the telecommunications domain”, Fuzzy Systems (FUZZ-IEEE), pp. 1-8, 2012.
[17]S. J.; M. S. F.; M. E. A., “Fuzzy type-1 and type-2 TSK modeling with application to solar power prediction”, 2012 IEEE Power and Energy Society General Meeting, pp. 1-6, 2012.
[18]Z. P.; K. Q.; Y. X., “Dynamic adaptive fuzzy neural-network identification and its application”, IEEE International on Systems, Man and Cybernetics, pp. 4974-4979, 2003.
[19]D. N.; R. K., “A fuzzy neural network learning fuzzy control rules and membership functions by fuzzy error back propagation”, IEEE International on Neural Networks, Vol.:2, pp. 1022-1027, 1993.
[20]Y. Z; X. Y.; X. C.; M. B., “Unmanned hybrid electric vehicles FNN control based on self-organized learning algorithm and supervised learning algorithm”, International Conference on Computer, Mechatronics Control and Electronic Engineering, Vol.:2, pp. 555-558, 2010.
[21]A. P. L.; K. F. F., “Back propagation using generalized least squares”, IEEE International on Neural Networks, Vol.:1, pp. 592-597, 1993.
[22]J. S. B.; A. A., “A novel method for medical disease diagnosis using artificial neural networks based on back propagation algorithm”, Confluence 2013: The Next Generation Information Technology Summit, pp. 55-61, 2013.
[23]A. S. S.; I. A. M.; S. M.; N. A., “Back propagation neural network with new improved error function and activation function for classification problem”, 2012 IEEE Symposium on Humanities, Science and Engineering Research, pp. 1359-1364, 2012.
[24]S. W., Z. L., Z. J., M. S., “Adaptive Control Based On Neural Network”, pp. 181-204, 2009.
[25]吳俊財, “EMU500型軔機系統－集電弓總成之概要說明”, 彰化機務段, 2014.
[26]T. C. L., C. C. W., I S. L., V. E. B., “Identifier based interval type-2 fuzzy tracking control”, Conference on Fuzzy Systems (FUZZ), July, 2013.
[27]Y. C. L., C. L. L. C. L. L., C. C. Y., ”Robust active vibration control for rail vehicle pantograph”, IEEE Trans. on Vehicular Technology, vol. 56, no. 4, pp. 1994-2004, 2007