研究生: |
林威廷 LIN WEI TING |
---|---|
論文名稱: |
基於人工智慧之可攜式電池診斷平台 Portable Battery Diagnostic Platform Based on Artificial Intelligence |
指導教授: |
林長華
Chang-Hua Lin |
口試委員: |
王見銘
Chien-Ming Wang 黃仲欽 Jonq-Chin Hwang 王永宜 Yung-Yi Wang |
學位類別: |
碩士 Master |
系所名稱: |
電資學院 - 電機工程系 Department of Electrical Engineering |
論文出版年: | 2020 |
畢業學年度: | 108 |
語文別: | 中文 |
論文頁數: | 150 |
中文關鍵詞: | 鋰電池 、人工智慧 、電量狀態 、健康狀態 |
外文關鍵詞: | lithium battery, artificial intelligence, state of charge, state of health |
相關次數: | 點閱:588 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
本文研製基於人工智慧之可攜式電池診斷平台。所提系統利用同步整流降壓型轉換器架構與Raspberry Pi單板電腦,對待測電池進行定電流與隨機電流的抽載,並藉此擷取待測電池之動態數據。所提電量狀態與健康狀態估測法則,利用機器學習的方法由大量的充放電數據取得電池內部動態特性,從而建立電池電量狀態與測量電壓變量之間的非線性關係,除了不需要特定的數學模型,也不需要花費時間等待電池的電化學反應,並可以輕易地擴展規格及解決其他影響因素。其次,除了可以在定電流抽載的情況下,估測電池初始電量與健康狀態;亦可於不同負載的情況下,即時估測電池之電量。再者,加入人機介面與電池診斷平台進行雙向溝通,除了可利用偵測電路蒐集主電路及待測電池之相關參數,並將資料傳送至人機介面顯示,亦可直接由人機介面對系統進行相關控制。最後,經訓練完成的模型實際進行電池電量狀態及健康狀態的推論,實測結果皆能與預期相符。
This thesis develops a portable battery diagnostic platform based on artificial intelligence. The dynamic characteristics of the tested battery are captured by the constant current and random current loading which is controlled by a synchronous buck converter and a raspberry pi computer. The proposed SOC and SOH estimation algorithm uses machine-learning technique to obtain the internal dynamics characteristics of battery from lots of charge-discharge data to establish the nonlinear relationship between the battery SOC and the differential voltage from measuring. This method requires neither a specific mathematical model and nor waiting time for electrochemical reaction of the battery, also can easily extend to higher specification and resolve other affecting factors. Secondly, in addition to estimating the SOH and initial SOC of tested battery under constant current loading conditions, the SOC of the tested battery also can be estimated in real time under random loading conditions. Furthemore, the human-machine interface(HMI) is added to the portable battery diagnostic platform for bidirectional communication. In addition to using the detection circuit to collect the relevant parameters and data of the main circuit and the tested battery and transmit it to the display of the HMI, the proposed approach can also be directly controlled by the HMI. Finally, the trained model is used to infer the SOC and SOH of the tested battery, the measured results are very close to expectations.
[1] M. Cacciato, G. Nobile, G. Scarcella and G. Scelba, "Real-Time Model-Based Estimation of SOC and SOH for Energy Storage Systems," IEEE Transactions on Power Electronics, vol. 32, no. 1, pp. 794-803, Jan. 2017.
[2] H. Chaoui, A. El Mejdoubi and H. Gualous, "Online Parameter Identification of Lithium-Ion Batteries With Surface Temperature Variations," IEEE Transactions on Vehicular Technology, vol. 66, no. 3, pp. 2000-2009, March 2017.
[3] R. Xiong, F. Sun, X. Gong and H. He, " Cell State-of-Charge Estimation for the Multi-cell Series-connected Battery Pack with Model bIas Correction Approach," Journal of Power Sources, vol. 242, pp. 699-713, May. 2013.
[4] A. T. Elsayed, C. R. Lashway and O. A. Mohammed, "Advanced Battery Management and Diagnostic System for Smart Grid Infrastructure," IEEE Transactions on Smart Grid, vol. 7, no. 2, pp. 897-905, March 2016.
[5] Q. Yu, R. Xiong, C. Lin, W. Shen and J. Deng, "Lithium-Ion Battery Parameters and State-of-Charge Joint Estimation Based on H-Infinity and Unscented Kalman Filters," IEEE Transactions on Vehicular Technology, vol. 66, no. 10, pp. 8693-8701, Oct. 2017.
[6] D. Andre, C. Appel, T. Soczka-Guth, D. Sauer, “Advanced mathematical methods of SOC and SOH estimation for lithium-ion batteries,” Journal of Power Sources, vol. 224, pp. 20-27, Oct. 2012.
[7] M. A. Hannan, M. S. H. Lipu, A. Hussain, and A. Mohamed, “A review of lithium-ion battery state of charge estimation and management system in electric vehicle applications: Challenges and recommendations,”Renewable Sustain. Energy, vol. 78, pp. 834–854, Oct. 2017.
[8] M. K. Hossain and S. M. R. Islam, "Battery Impedance Measurement Using Electrochemical Impedance Spectroscopy Board," 2017 2nd International Conference on Electrical & Electronic Engineering (ICEEE), Rajshahi, 2017, pp. 1-4.
[9] G. Wu, R. Lu, C. Zhu, and C. C. Chan, “State of charge estimation for NiMH Battery based on electromotive force method,” In Proc. IEEE Veh. Power Propulsion Conf., Harbin, China, 2008, pp. 1–5.
[10] 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 Transactions on Vehicular Technology, vol. 54, no. 3, pp. 783-794, May 2005.
[11] G. L. Plett, “Extended Kalman filtering for battery management systems of LiPB-based HEV battery packs,” Journal of Power Sources, vol. 134, pp. 252–261, Aug. 2004.
[12] G. O. Sahinoglu, M. Pajovic, Z. Sahinoglu, Y. Wang, P. V. Orlik and T. Wada, "Battery state-of-charge estimation based on regular/recurrent Gaussian process regression,"IEEE Trans. Ind. Electron., vol. 65, no. 5, pp. 4311-4321, May 2018.
[13] Y. Bengio, P. Simard and P. Frasconi, "Learning long-term dependencies with gradient descent is difficult",IEEE Trans. Neural Netw., vol. 5, no. 2, pp. 157-166, Mar. 1994.
[14] S. Hochreiter and J. Schmidhuber, "Long short-term memory",Neural Comput., vol. 9, no. 8, pp. 1735-1780, 1997.
[15] H. Dai, G. Zhao, M. Lin, J. Wu and G. Zheng, "A Novel Estimation Method for the State of Health of Lithium-Ion Battery Using Prior Knowledge-Based Neural Network and Markov Chain,"IEEE Transactions on Industrial Electronics, vol. 66, no. 10, pp. 7706-7716, Oct. 2019, doi: 10.1109/TIE.2018.2880703.
[16] J. Zhou, Z. He, M. Gao and Y. Liu, "Battery state of health estimation using the generalized regression neural network,"2015 8th International Congress on Image and Signal Processing (CISP), Shenyang, 2015, pp. 1396-1400, doi: 10.1109/CISP.2015.7408101.
[17] L. Lu, X. Han, J. Li, J. Hua and M. Ouyang, "A review on the key issues for lithium-ion battery management in electric vehicles",” Journal of. Power Sources, vol. 226, pp. 272-288, Mar. 2013.
[18] R. Karshenas et al., "Bidirectional dc-dc converters for energy storage systems," Energy Storage in the Emerging era of Smart Grids, September 2011.
[19] 張瓊仁,“鎳氫電池容量管理之研究”,國立中山大學電機工程系碩士論文,西元2005年七月。
[20] Battery University, BU-216 [Online]. Available:
https://is.gd/qxgGlv
[21] Sanyo/Panasonic, UR18650NSX Datasheet [Online].Available:
https://is.gd/LJTqur
[22] Q. Xu, J. Xiao, P. Wang, X. Pan and C. Wen, "A Decentralized Control Strategy for Autonomous Transient Power Sharing and State-of-Charge Recovery in Hybrid Energy Storage Systems," IEEE Transactions on Sustainable Energy, vol. 8, no. 4, pp. 1443-1452, Oct. 2017.
[23] 石力維,“基於微控制器之鋰離子電池即時診斷系統”,大同大學電機工程研究所碩士論文,西元2016年七月。
[24] 林頂立,”類神經網路於鉛酸電池殘電量偵測之應用.” 國立高雄應用科技大學電機工程系碩士論文,西元2007年六月。
[25] C. Weng, J. Sun and H. Peng “A unified open-circuit-voltage model of lithium-ion batteries for state-of-charge estimation and state-of-health monitoring,” Journal of Power Sources, vol. 258, pp.228-237, Jul, 2014.
[26] 陳冠中,“具能量回收之可攜式在線電池診斷平台”,台灣科技大學電機工程研究所碩士論文,西元2019年七月。
[27] J. H. Aylor, A. Thieme and B. W. Johnso, "A battery state-of-charge indicator for electric wheelchairs," IEEE Transactions on Industrial Electronics, vol. 39, no. 5, pp. 398-409, Oct. 1992.
[28] Lygte, Sanyo/Panasonic UR18650NSX 2600mAh (Red) [Online]. Available: http://t.cn/EKatwXO
[29] W. Li, L. Liang, W. Liu and X. Wu, "State of Charge Estimation of Lithium-Ion Batteries Using a Discrete-Time Nonlinear Observer," IEEE Transactions on Industrial Electronics, vol. 64, no. 11, pp. 8557-8565, Nov. 2017.
[30] F. Yang, Y. Xing, D. Wang and K.-L. Tsui, "A comparative study of three model-based algorithms for estimating state-of-charge of lithium-ion batteries under a new combined dynamic loading profile", Appl. Energy, vol. 164, pp. 387-399, Feb. 2016.
[31] F. Yang, D. Wang, Y. Xing and K.-L. Tsui, " Prognostics of Li(NiMnCo)O 2 -based lithium-ion batteries using a novel battery degradation model ", Microelectron. Rel., vol. 70, pp. 70-78, Mar. 2017.
[32] Joachims, T., “Learning to Classify Text Using Support Vector Machines: Methods, Theory and Algorithms.” Kluwer Academic Publishers, 2002.
[33] Furey, T. S. et al., “Support vector machine classification and validation of cancer tissue samples using microarray expression data.” Bioinformatics, Volume 16, pp. 906- 914, 2000.
[34] Pavlidis, P., Cai, J., Weston, J. & Grundy, W. N., “Gene Functional Classification From Heterogeneous Data.” The Fifth International Conference on Computational Molecular Biology. New York: ACM Press, p. 249–255, 2001.
[35] Ding, C. & Dubchak, I, “Multi-class protein fold recognition using support vector machines and neural networks.” Bioinformatics, Volume 17, p. 349–358, 2001.
[36] Bahlmann, C., Haasdonk, B. & Burkhardt, H, “On-Line Handwriting Recognition with Support Vector Machines: A Kernel Approach.” Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR'02). Washington, DC, USA : IEEE Computer Society, p. 49, 2002.
[37] Moghaddam, B. & Yang, M.-H, “Learning Gender with Support Faces.” IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5), pp. 707-711, 2002.
[38] 林頂立,“類神經網路於鉛酸電池殘電量偵測之應用”,國立高雄應用科技大學電機工程系碩士論文,西元2007年六月。
[39] A. Affanni, A. Bellini, C. Concari, G. Franceschini, E. Lorenzani, and C. Tassoni, “EV battery state of charge:Neural network based estimation,” Electric Machines and Drives Conference, vol. 2, pp. 684– 688, 2002.
[40] H. X. Lu, Y. Lu, Z. F. T, S. J. W, “SOC Dynamic Power Management Using Artificial Neural Network”, The Sixth International Conference On Intelligent Systems Design and Applications (ISDA ’06), 2006
[41] Anand, I; Mathur, B.L., “State of charge estimation of lead acid batteries using neural networks,” 2013 International Conference on Circuits, Power and Computing Technologies (ICCPCT), pp. 596, 599, Mar. 20-21, 2013
[42] H.-T. Lin, T.-J. Liang, and S.-M. Chen, “Estimation of battery state of health using probabilistic neural network,” IEEE Transactions on Industrial Informatics, vol. 9, no. 2, pp. 679–685, May 2013.
[43] J. Szoplik, ‘‘Forecasting of natural gas consumption with artificial neural networks,’’ Energy, vol. 85, pp. 208–220, Jun. 2015.
[44] S. Hochreiter and J. Schmidhuber. ‘‘Long short-term memory.’’ Neural Computation, 9(8):1735–1780, 1997.
[45] Nair, V., & Hinton, G. E. ‘‘Rectified linear units improve restricted boltzmann machines.’’ The 27th international conference on machine learning, pp. 807-814, 2010.
[46] Graves, A., Mohamed, A. R., & Hinton, G., ‘‘Speech recognition with deep recurrent neural networks.’’ 2013 IEEE international conference on speech and signal processing, pp. 6645-6649, 2013.
[47] Wang, S., & Jiang, J., ‘‘Learning natural language inference with LSTM.’’ arXiv preprint, arXiv:1512.08849, 2015.
[48] You, Q., Jin, H., Wang, Z., Fang, C., & Luo, J., ‘‘Image captioning with semantic attention.’’ The IEEE Conference on Computer Vision and Pattern Recognition, pp. 4651-4659, 2016.
[49] F. Yang, X. Song, F. Xu and K. Tsui, "State-of-Charge Estimation of Lithium-Ion Batteries via Long Short-Term Memory Network," in IEEE Access, vol. 7, pp. 53792-53799, 2019
[50] H. Ma, Q. Guo, X. Han and L. Chen, "Energy recycling load system with a high gain DC-DC converter for ultra low voltage power supplies," 2013 IEEE International Symposium on Industrial Electronics, Taipei, 2013, pp. 1-6.
[51] K. I. Hwu. and Y. T. Yau, “Active Load for Burn-in Test of Buck-Type DC-DC Converter with Ultra-Low Output Voltage,” in Conf. Rec. IEEE APEC’08, pp. 635-638, 2008.
[52] Ming-Tsung Tsai and C. Tsai, "Energy recycling for electrical AC power source burn-in test," IEEE Transactions on Industrial Electronics, vol. 47, no. 4, pp. 974-976, Aug. 2000.
[53] Hyunsik Jo, Byung-Moon Han and Hanju Cha, "Grid-connected Battery Test System with AC regenerating capability," 2014 IEEE International Energy Conference (ENERGYCON), Cavtat, 2014, pp. 82-86.
[54] Chroma Model 17020 Datasheet [Online]. Available:
http://www.chroma.com.tw/product/17020_Regenerative_Battery_Pack.htm
[55] C. Wang, C. Lin and H. Lin, "High-efficiency and low-stress ZVS-PWM bidirectional DC/DC converter for battery charger," in Conf. Rec. 6th IEEE Conf. on Industrial Electronics and Applications, Beijing, 2011, pp. 1185-1190.
[56] L. Chen, N. Chu, C. Wang and R. Liang, "Design of a reflex-based bidirectional converter with the energy recovery function," IEEE Transactions on Industrial Electronics, vol. 55, no. 8, pp. 3022-3029, Aug. 2008.
[57] Pei-Hsuan Cheng and Chern-Lin Chen, "A high-efficiency fast charger for lead-acid batteries," in Cof. Rec. IEEE 28th Annu. Conf. of the Industrial Electronics Society, Sevilla, 2002, pp. 1410-1415 vol.2.
[58] 洪裕桓,“智慧型鋰電池管理系統之研製”,國立中山大學電機工程系碩士論文,西元2005年六月
[59] 梁耿儒,“以微控制器為基礎具有電量估測之鋰鈷電池充電器”,大同大學電機工程研究所碩士論文,西元2012年七月
[60] Eaton, "XV3550-2R7307-R datasheet," December 2017.
[61] 吳義利,“切換式電源轉換器原理與應用技術設計(實例設計導向)” 2015年6月。
[62] Allegro Micro Systems, ACS723LLCTR-10AB-T, " High-Accuracy, Galvanically Isolated Current Sensor IC with Small Footprint SOIC8 Package" 2018.
[63] Texas Instruments, OPA2227, “HIGH PRECISION, LOW NOISE OPERATIONAL AMPLIFIER,” 2012.
[64] Analog Devces, "AD596/AD597," 1998.
[65] Toshiba, "TLP250H, TLP250HF Datasheet," 2015.
[66] Minmax, "MCW103, dc/dc converter 3W datasheet," 2011
[67] Microchip, "Assembler/linker/librarian user's guide," 2005.
[68] The Modbus Organization, ‘‘Modbus Application Protocol Specification.’’ V1.1b3, Retrieved March 31, 2009
[69] The Modbus Organization, ‘‘MODBUS over serial line specification and implementation guide.’’ V1.02, Retrieved Dec. 20, 2006
[70] 陳碩,“如何用C++開發頂級多執行緒網路函數庫Muduo” 2015。
[71] Williams,“C++並行程式設計實戰手冊:多執行緒實務“ 2015。
[72] Cruz, Eduardo H. M., ‘‘Thread and data mapping for multicore systems improving communication and memory accesses.’’2018
[73] S. Saxena, C. Hendricks and M. Pecht, "Cycle life testing and modeling of graphite/LiCoO2 cells under different state of charge ranges", J. Power Sources, vol. 327, pp. 394-400, 2016
[74] H. Dai, G. Zhao, M. Lin, J. Wu and G. Zheng, "A Novel Estimation Method for the State of Health of Lithium-Ion Battery Using Prior Knowledge-Based Neural Network and Markov Chain," in IEEE Transactions on Industrial Electronics, vol. 66, no. 10, pp. 7706-7716, Oct. 2019
[75] T. Dozat., “Incorporating nesterov momentum into adam.” International Conference on Learning Representations, 2016.
[76] Yurii Nesterov. “A method of solving a convex programming problem with convergence rate O(1/k2).” Soviet Mathematics Doklady, volume 27, pages 372–376, 1983.
[77] D Kingma, J Ba, “Adam: A method for stochastic optimization.” International Conference on Learning Representation, 2015