本研究以兩輪平衡車(Two-wheeled vehicle)為實驗平台，建構一套監控電動車電源的智慧型系統。因為兩輪平衡車為一倒單擺系統，它有著動態平衡以及負載重量不確定等特性，因此電壓電流的變化大，所以也較難準確且有效地估測載具電池殘電量(State of charge、SOC)、評估尚可工作的時間以及計算可行走的距離等。本文從能量的角度出發，去評估電池在工作狀態下的耗損狀況。首先，利用可程式規劃電子負載與直流電源供應器，對電池組進行特定形式的充放電實驗，找出電池工作時的耗損特性，進一步利用倒傳遞類神經網路(Back Propagation Neural Network)求出電池耗損的特性曲線。在兩輪平衡車方面，同時製作一具有藍牙通訊能力的電壓電流量測模組嵌入載具中。接下來，在電腦上利用所求出的電池耗損特性曲線設計成估測電池電量的演算法。最後，透過實際騎乘兩輪平衡車實驗，實驗結果顯示車上電池電量可有效的估測。

This thesis using the two-wheeled vehicle as an experimental platform constructs an intelligent system to monitor the power of the two-wheeled vehicle. Two-wheeled vehicle which has the characteristics of dynamic balance and uncertain loading weights is an inverted pendulum system. Because its fluctuations of voltage and current are violent, it is difficult to estimate the state of charge (SOC), and the surplus time and distance of operation correctly and efficiently. Therefore, this thesis mainly studies the power estimation of the two-wheeled vehicle. First of all, based on programmable electronic load and DC power supply, some experiments of charge and discharge are performed in the batteries of the two-wheeled vehicle. Using the experimental data finds the loss features of the batteries. Then, using back propagation neural network approximates the loss features of the batteries. Moreover, a voltage and current measuring model with bluetooth communication is built and integrated into the electric control system of the two-wheeled vehicle. Next, an algorithm to estimate the battery power of the two-wheeled vehicle is developed. Finally, the real experiment result shows that the proposed method is effective.

[1] SEGWAY 官方網站，取自http://www.segway.com/，2014。
[2] IL-Song Kim, “Technique for Estimating the State of Health of Lithium Batteries Through a Dual-Sliding-Mode Observer,” IEEE Trans. Power Electron., vol. 25, no. 4, pp. 1013–1022, Jun. 2010.
[3] B. S. Bhangu, P. Bentley, D. A. Stone, and C. M. Bingham, “Nonlinear Observers for Predicting State-of-Charge and State-of-Health of Lead-Acid Batteries for Hybrid-Electric Vehicles,” IEEE Trans. Veh. Techno. vol. 54, no. 3, pp. 783-794, May 2005.
[4] Jonghoon Kim, and B. H. Cho, “State-of-Charge Estimation and State-of-Health Prediction of a Li-Ion Degraded Battery Based on an EKF Combined With a Per-Unit System,” IEEE Trans. Veh. Techno. vol. 60, no. 9, pp. 4240-4260, Nov 2011.
[5] Larry W. Juang, Phillip J. Kollmeyer, Thomas M. Jahns, and Robert D. Lorenz, “Improved Nonlinear Model for Electrode Voltage–Current Relationship for More Consistent Online Battery System Identification,” IEEE Trans. Ind. Appl. vol. 49, no. 3, pp. 1480-1488, May 2011.
[6] Vasebi, Amir, Maral Partovibakhsh, and S. Bathaee. "A novel combined battery model for state-of-charge estimation in lead-acid batteries based on extended Kalman filter for hybrid electric vehicle applications." Journal of Power Sources 174.1 (2007): 30-40.
[7] Sepasi, Saeed, Reza Ghorbani, and Bor Yann Liaw. "A novel on-board state-of-charge estimation method for aged Li-ion batteries based on model adaptive extended Kalman filter." Journal of Power Sources 245 (2014): 337-344.
[8] Sepasi, Saeed, Reza Ghorbani, and Bor Yann Liaw. "A novel on-board state-of-charge estimation method for aged Li-ion batteries based on model adaptive extended Kalman filter." Journal of Power Sources 245 (2014): 337-344.
[9] Gholizadeh, Mehdi, and Farzad R. Salmasi. "Estimation of State of Charge, Unknown Nonlinearities, and State of Health of a Lithium-Ion Battery Based on a Comprehensive Unobservable Model." Industrial Electronics, IEEE Transactions on 61.3 (2014): 1335-1344.
[10] Hsieh, Guan-Chyun, Liang-Rui Chen, and Kuo-Shun Huang. "Fuzzy-controlled Li-ion battery charge system with active state-of-charge controller." Industrial Electronics, IEEE Transactions on 48.3 (2001): 585-593.
[11] Lee, Jaemoon, Oanyong Nam, and B. H. Cho. "Li-ion battery SOC estimation method based on the reduced order extended Kalman filtering." Journal of Power Sources 174.1 (2007): 9-15.
[12] Ceraolo, Massimo. "New dynamical models of lead-acid batteries." Power Systems, IEEE Transactions on 15.4 (2000): 1184-1190.
[13] Sinkaram, Chelladurai, Kausillyaa Rajakumar, and Vijanth Asirvadam. "Modeling battery management system using the lithium-ion battery." Control System, Computing and Engineering (ICCSCE), 2012 IEEE International Conference on. IEEE, 2012.
[14] 李承洲，「獨立充電儲能系統設計」，碩士論文，國立臺灣師範大學應用電子科技學系碩士班，臺灣，2011。
[15] 黃嘉煒，「具有啟動保護之獨立充電儲能系統設計」，碩士論文，國立臺灣師範大學應用電子科技學系碩士班，臺灣，2013。
[16] Power Sonic官方網站，取自http://www.power-sonic.com/index.php，2014。
[17] 承德科技股份有限公司 官方網站，取自http://www.chentech.com.tw/index.aspx，2014。
[18] 台灣湯淺電池 官方網站，取自http://www.yuasa.com.tw/index.php，2014。
[19] Bhangu, Bikramjit S., et al. "Nonlinear observers for predicting state-of-charge and state-of-health of lead-acid batteries for hybrid-electric vehicles." Vehicular Technology, IEEE Transactions on 54.3 (2005): 783-794.
[20] Wang, Haiying, et al. "Study on State of Charge Estimation of Batteries for Electric Vehicle." ASP 2013, ASTL Vol. 18, pp. 10-14, (2013).
[21] Shaban, Khaled, Ayman El-Hag, and Andrei Matveev. "A cascade of artificial neural networks to predict transformers oil parameters." Dielectrics and Electrical Insulation, IEEE Transactions on 16.2 (2009): 516-523.
[22] 羅華強，「類神經網路-MATLAB的應用」，高立圖書，第三版，2011。
[23] González-Longatt, Francisco M. "Circuit based battery models: a review." Congreso Iberoamericano de estudiantes De Ingenieria Electrica. Cibelec. 2006.