本研究結合人工類神經網路法與內阻量測法，應用於鋰離子電池殘電量估測，不同於一般僅以電壓與電流為輸入參數之類神經網路研究，輸入層增加重要參數：電池內阻值，與電池電壓、電流作為外部輸入，設計一具外源輸入非線性自迴歸(nonlinear autoregressive with exogenous input , NARX)之遞迴式類神經網路模型，並與倒傳遞類神經網路比較在同基準下模擬結果之差異，實驗證明此架構不僅提高類神經網路的收斂速度，縮短其平均執行時間，誤差均方更有所改善，能夠很好地反映出測量之精準度。本論文亦探討此架構應用於電池直流內阻與交流內阻之區別研究。

This paper combines the artificial neural network (ANN) method and the internal resistance measuring method, which is designed for the state of charge (SOC) estimation of lithium-ion battery. It is different from the general neural network research that only uses voltage and current as input parameters. The input layer adds important parameters : the internal resistance of the battery, and the battery voltage and current as external inputs. We design a recurrent neural networks (RNN) model with non-linear autoregressive with exogenous input (NARX). The network compares the difference between the simulation results under the same benchmark with the back-propagation neural networks (BPNN). Experiments show that this architecture not only improves the convergence speed of the neural network, but also shortens its average execution time, and the mean-square error is improved. It is a good indicator of the accuracy of the measurement. This paper also discusses the application of this architecture to the difference between DC internal resistance and AC internal resistance.

摘要.......................i
Abstract.......................ii
誌謝.......................iii
目錄.......................iv
表目錄.......................vi
圖目錄.......................vii
第一章 緒論.......................1
1.1 研究動機與目的.......................1
1.2 研究方法.......................1
1.3 論文大綱.......................2
第二章 鋰離子電池介紹與內阻量測方法.......................3
2.1 電池簡介.......................3
2.2 鋰離子電池介紹與原理.......................4
2.3 鋰離子電池模型.......................6
2.4 電池內阻量測方法.......................10
2.4.1 直流法.......................10
2.4.2 交流法.......................11
2.4.3 四線式量測.......................14
2.4.4 阻抗計算.......................16
2.5 電池殘電量估測法.......................17
第三章 交流法內抗量測系統架構.......................24
3.1 系統與電路架構.......................24
3.2 激勵訊號產生電路.......................25
3.3 推挽式放大器.......................28
3.4 儀表放大器.......................30
3.5 帶通濾波器.......................32
3.6 精密全波整流器.......................34
3.7 峰值檢測器.......................36
3.8 電壓量測電路.......................39
3.9 類比數位轉換器.......................40
第四章 類神經網路.......................42
4.1 神經元模型.......................43
4.2 轉移函數.......................45
4.3 類神經網路架構.......................47
4.4 網路學習方式.......................48
4.5 倒傳遞類神經網路.......................49
4.6 遞迴式類神經網路.......................51
4.7 類神經網路設計.......................57
第五章 實驗方法與流程.......................60
5.1 實驗架構.......................60
5.2 研究使用電池介紹.......................62
5.3 實驗流程.......................65
5.4 實驗儀器介紹.......................72
第六章 實驗結果與分析.......................76
6.1 BPNN-0.5C、1C、2C模擬結果(交流內阻分析).......................77
6.1.1 0.5C放電速率-BPNN模擬.......................78
6.1.2 1C放電速率-BPNN模擬.......................80
6.1.3 2C放電速率-BPNN模擬.......................82
6.2 NARX-0.5C、1C、2C模擬結果(交流內阻分析).......................84
6.2.1 0.5C放電速率- NARX模擬.......................86
6.2.2 1C放電速率-NARX模擬.......................89
6.2.3 2C放電速率-NARX模擬.......................92
6.3 BPNN與NARX模擬結果比較(交流內阻分析).......................95
6.4 直流內阻模擬結果分析.......................99
6.4.1 BPNN模擬結果.......................100
6.4.2 NARX模擬結果.......................103
6.5 BPNN與NARX模擬結果比較(直流內阻分析).......................107
第七章 結論與未來展望.......................109
7.1 結論.......................109
7.2 未來展望.......................109
參考文獻.......................110
Extended Abstract.......................113

[1]Zechang Sun, Xuezhe Wei and Haifeng Dai, “Battery management system in the China-made ‘‘Start’’ series FCHVs”, Proceedings of IEEE international vehicle power and propulsion conference, pp. 1-6, 2008.
[2]Xu Zhang, Yujie Wang, Duo Yang and Zonghai Chen, “An on-line estimation of battery pack parameters and state-of-charge using dual filters based on pack model”, Energy, Vol. 115, pp. 219-229, November 2016.
[3]R. Mingant, J. Bernard and V. Sauvant-Moynot, “Novel state-of-health diagnostic method for Li-ion battery in service”, Applied Energy, Vol. 183, pp. 390-398, December 2016.
[4]Haifeng Dai, Xuezhe Wei, Zechang Sun, Jiayuan Wang and Weijun Gu, “Online cell SOC estimation of Li-ion battery packs using a dual time-scale Kalman filtering for EV applications”, Applied Energy, Vol. 95, pp. 227-237, July 2012.
[5]L. M. Hofland, E.J. Stofel,and R.K. Taenaka, “Galileo probe Li-So2 battery cell life testing,“ IEEE Aerosp. Electron. Syst., pp. 14-18, 1996.
[6]Pang, S., Farrell, J., Barth, M., “Battery state-of-chatge estimation,” Proceedings of the American Control Conference, Vol. 2, pp. 1644-1649, June 2001.
[7]P. Singh, C. Fennie, and D. Reisner, “Fuzzy logic modelling of state-of-charge and available capacity of nickel /metal hydride batteries,” Vol. 136, pp. 322–333, 2004.
[8]C. Hu, B. D. Youn, and J. Chung, “A multiscale framework with extended Kalman filter for lithium-ion battery SOC and capacity estimation,” Applied Energy, Vol. 92, pp. 694-704, 2012.
[9]Ala A. Hussein, “Capacity Fade Estimation in Electric Vehicle Li-Ion Batteries Using Artificial Neural Networks,” IEEE Transactions on Industry Applications, Vol. 51, No. 3, May/Jun 2015.
[10]曾子倫、劉煥彩，“手持式鋰離子電池交流內阻量測系統開發設計”，國立虎尾科技大學電機工程系碩士論文，2017。
[11]甘宗達、劉煥彩，“ 基於電化學阻抗譜建立電池模型參數量測系統設計”，國立虎尾科技大學電機工程系碩士論文，2017。
[12]Hicham Chaoui, “State of Charge and State of Health Estimation for Lithium Batteries Using Recurrent Neural Networks”, IEEE Transactions on Vehicular Technology, Vol. 66, No. 10, October 2017.
[13]Uwe Tröltzsch, Olfa Kanoun, Hans-Rolf Tränkler, “Characterizing aging effects of lithium ion batteries by impedance spectroscopy”, Electrochimica Acta, Vol. 51, pp. 1664-1672, January 2006.
[14]葉家銘，“以DSP為控制單元之智慧型電源管理”，國立中山大學電機工程學系碩士論文，七月，2003。
[15]ShunPin Hsu, ChunLiang Lin, JenYa Wu, “Balancing charge/discharge management for series/parallel”, Industrial Electronics and Applications(ICIEA), July 2012.
[16]黃可龍，劉素琴，王兆翔，“鋰離子電池原理與技術”， 五南出版社，2010。
[17]Sony Energy Devices Corporation. “Keywords to understanding Sony Energy Devices ”, 2015.
[Online] Available：http://www.sonyenergy-devices.co.jp/
[18]Jiang Zhou, “Lithium metal microreference electrodes and their applications to Li-ion batteries”, Eindhoven: Technische Universiteit Eindhoven, 2007.
[19]賴世榮，“智慧型鋰離子電池殘存電量估測之研究”，國立中山大學，電機工程學系碩士論文，十月，2004。
[20]李政勳，“具有等效模型SOC估測於鈷酸鋰電池之電量平衡系統”，逢甲大學，電機工程學系碩士論文，七月 2015。
[21]林峻生，“電動機車剩餘電量量測及能量管理系統之研製”，國立彰化師範大學電機工程學系碩士論文，一月，2006。
[22]“Basics of Electrochemical Impedance Spectroscopy”, GAMRY Instruments Inc.
[Online] Available：https://www.gamry.com/application-notes/EIS/basics-of-electrochemical-impedance-spectroscopy/
[23]楊昇晃，“微型燃料電池設計、製作與電化學阻抗量測分析”，國立中山大學，機械與機電工程學系碩士論文，六月，2005。
[24]Metrohm, “Electrochemical Impedance Spectroscopy (EIS) Part 3 – Data Analysis”, Metrohm Application Notes, July 2011.
[25]Metrohm, “Electrochemical Impedance Spectroscopy (EIS) Part 4 – Equivalent Circuit Models”, Metrohm Application Notes, July 2011.
[26]MIT, “Equivalent Circuit Models Lecture 6: Impedance of Electrodes”, MIT OpenCourseWare, Spring 2014.
[27]Hans-Georg Schweiger, Ossama Obeidi, Oliver Komesker, André Raschke, Michael Schiemann, Christian Zehner, Markus Gehnen, Michael Keller and Peter Birke, “Comparison of Several Methods for Determining the Internal Resistance of Lithium Ion Cells”, Sensors Open Access Journal, pp. 5604-5625, June 2010.
[28]Tektronix, “Overview of Two-Wire and Four-Wire(Kelvin) Resistance Measurements”, Tektronix Application Notes, September 2012.
[29]Analog Devices, “Basic Three Op Amp In-Amp Configuration”, Analog Devices University Program Online Teaching Materials, MT-063.
[30]Texas Instruments, “Analysis of the Sallen-Key Architecture”, Texas Instruments Application Report, SLOA024B, September 2002.
[31]洪嘉男、劉煥彩，“鉛酸電池交流內阻量測系統開發設計”，國立虎尾科技大學電機工程系碩士論文，2016。
[32]Jim Karki, “Active Low-Pass Filter Design”, Texas Instruments Application Report, SLOA049B, September 2002.
[33]ShingLig Wu, HungCheng Chen, ShuoRong Chou, “Fast Estimation of State of Charge for Lithium-Ion Batteries”, Vol. 7, pp.3438－3452, March 2014.
[34]LiangRui Chen, ShingLih Wu, ChungPing Chou, TsairRong Chen, “Design of Sinusoidal Current Charger with Optimal Frequency Tracker for Li-ion Battery”, International Power Electronics Conference, June 2010.
[35]LiangRui Chen, ShingLih Wu, TsairRong Chen, “Improving Battery Charging Performance by Using Sinusoidal Current Charging with the Minimum AC Impedance Frequency”, IEEE International Conference on Sustainable Energy Technologies(ICSET), December 2010.
[36]Keithley Instrument, Inc, “Overview of Two-Wire and Four-Wire(Kelvin) Resistance Measurements”, 2012.
[37]Bernard A. Boukamp, “Electrochemical Impedance Spectroscopy”, Leiden University, November 2008.
[38]G. Alber, and M.W. Migliaro, “Impedance testing-is it a substitute for capacity tests?” Telecommunications Energy Conference, pp.245-249,1994.
[39]Configuring the bq27010/210 for Gas Gauge Application, Texas Instruments, February 2007.
[40]馬凱文、連國龍，“鉛酸電池能效管理系統” ，國立台灣科技大學電機工程系碩士論文，2014
[41]Analog Devices Inc, "AD620 Datasheet", 2003.
[42]Texas Instrument Inc, “Active Filter Design Techniques”, 2008.
[43]Bonnie Baker, “How delta-sigma ADCs work, Part1”, Texas Instrument Inc, September 2016.
[44]Analog Devices Inc, “ADC Architectures III：Sigma-Delta ADC Basics”, 2009.
[45]Microchip Technology Inc., “類比數位轉換器設計指南”。
[46]Robert Hecht-Nielsen, “Neurocomputing”, Addison-Wesley Publishing Company, 1990.
[47]羅華強，“類神經網路―MATLAB的應用”，高立圖書有限公司，2011。
[48]黃聰亮，“動態類神經系統”，2012。
[Online] Available：https://www.slideshare.net/vincent8899/ss-11982639
[49]Lynn，”機器學習的衰頹興盛：從類神經網路到淺層學習”，股感知識庫，2016。[Online] Available：https://www.stockfeel.com.tw/
[50]林頂立、吳坤德，“類神經網路應用於鉛酸電池殘電量估測之研究”，國立高雄應用科技大學電機工程系碩士論文，2007。
[51]Pengfei Ni，”遞迴神經網路”，Gitbook，2017。
[Online] Available：https://feisky.xyz/machine-learning/rnn/
[52]Ashing Tsai，” 深度學習(3)--循環神經網絡(RNN, Recurrent Neural Networks)”，2017。
[Online] Available：http://arbu00.blogspot.com/2017/05/3-rnn-recurrent-neural-networks.html
[53]The MathWorks, Inc. ,” Design Time Series NARX Feedback Neural Networks”。
[Online] Available：https://ww2.mathworks.cn/help/nnet/ug/design-time-series-narx-feedback-neural-networks.html
[54]許佑綸、楊谷洋，”使用遞迴型神經網路之肌電圖動態動作預測機制”，國立交通大學電機與控制工程系碩士論文，七月，2008。
[55]Narendra, K. S. and Parthasarathy, K., “Identification and control of dynamical systems using neural networks,” IEEE Transactions on Neural Networks, Vol. 1, no. 1, pp. 1045-9227, 1990.
[56]SANYO Energy(U.S.A.) Corporation.,” Panasonic Lithium Ion NCR18650B”, 2012.
[Online] Available：https://www.batteryspace.com/prod-specs/NCR18650B.pdf
[57]Good Will Instrument Co., Ltd., ”GBT-2000 Battery Test System User’s Guide”, 2010.
[58]HIOKI E.E. Corporation, “BATTERY HTESTER 3554”, 2010.
[59]林庭毅、吳順德，”基於多尺度方均根、多尺度熵費雪法與倒傳遞網路之軸承錯誤診斷系統”，國立臺灣師範大學碩士論文，六月，2012。
[60]趙景明、梁淑芳，「導入LM之平行倒傳遞演算法」，資訊管理展望，第8卷，第2期，第85~108頁，12月，2006年。
[61]M.I.A Lorakis, “a Brief Description of the Levenberg-Marquardt Algorithm Implemented by levmar,” February 2005.
[Online] Available：www.ics.forth.gr/~lourakis/levmar/levmar.pdf
[62]黃如斌、蔡明忠，”應用倒傳遞類神經網路於太陽電池模組之品質評價研究”，國立台灣科技大學自動化及控制研究所碩士論文，一月，2013。
[63]劉信成、蘇朝墩，”應用多元迴歸與倒傳遞神經網路預測企業獲利能力之研究”，國立清華大學工業工程與工業管理系碩士論文，六月，2018。