隨著科技的發展，在能源議題越發受到重視的今天，發電與儲電已然是對未來發展與環境都極為重要的一環。而在其中也發展出了各種的電力儲存設備，例如各式鋰離子電池 (Lithium ion Battery)與超級電容器 (Electrostatic Double Layer Capacitor)等，當 然也有著各種預測其壽命與健康度的方式。而在現今，機器學習已成處理 大量資料與數據的主流方式之一， 各式演算法對資料的型態、類型都會有不一樣的準確度與適用性。
本文旨在探討基於機器學習的 鋰電池健康度預測模型之建立 。本文選用 NASA公開數據庫中的實驗數據，並透過比對所研究之機器學習演算法的訓練結果與測試果的數據，篩選出較適合建立鋰離子電池健康度預測模型的演算法 。 根據實驗結果， 線性回歸（ Linear Regression ，LR） 有最好的決定係數（ R Squared ，R2） 和 均方根誤差（Root Mean Square Error ，RMSE），且沒有過擬合 的情況，為最適合的演算法；而 SVMCubic的決定函數值為負值 ，為最不適合此資料
的演算法。

With the advancement of technology, as energy issues become increasingly important today, power generation and storage have become crucial aspects for future development and the environment. Various energy storage devices have been developed, including various types of lithium ion batteries and electrostatic double layer capacitors. Various methods have also been developed to predict their lifespan and health. In the present era, machine learning has become a mainstream approach for handling large amounts of data. Different algorithms exhibit varying accuracy and applicability based on the data types and patterns.
This thesis aims to explore the use of algorithms for lithium ion battery state of health (SOH) models. The study utilizes experimental data from NASA's public database, comparing the training and testing results of various algorithms to identify the most suitable and least suitable algorithms for estimating the SOH model of lithium ion batteries. According to the obtained results, Linear Regression demonstrates the best R Squared and RMSE values, with no overfitting, making it the most suitable algorithm. while SVMCubic exhibits a negative R Squared value, making it the least suitable algorithm for these utilized data.

[1] B. Saha and K. Goebel. “Battery Data Set”, NASA Prognostics Data Repository(2009-2010), NASA Ames Research Center, Moffett Field, CA. from:https://www.nasa.gov/intelligent-systems-division/discovery-and-systems-health/pcoe/pcoe-data-set-repository/
[2] 高柏科技股份有限公司(2022/9/5)。從溫度效應對電池包效率之影響了解提高電池效能20%之可行性。取自：https://www.materialsnet.com.tw/DocView.aspx?id=51334
[3] Stroe D.-I., Swierczynski M., Stroe A.-I., Laerke R., Kjaer P.C., Teodorescu R., "Degradation Behavior of Lithium-Ion Batteries Based on Lifetime Models and Field Measured Frequency Regulation Mission Profile" in IEEE Transactions on Industrial Electronics, vol. 52, no. 6, pp. 5009-5018, 2016.
[4] R. Klein, N. A. Chaturvedi, J. Christensen, J. Ahmed, R. Findeisen and A. Kojic, "Optimal charging strategies in lithium-ion battery" Proceedings of the 2011 American Control Conference, San Francisco, CA, USA, pp. 382-387, 2011
[5] 陳明達，「基於使用者特性之鋰離子電池充電程序最佳化」，國立交通大學資訊學程碩士論文，民國九十九年七月。
[6] 高郁芩，「具健康狀態估測之鋰離子電池充電法評估」，台灣科技大學電機工程碩士論文，民國一一二年六月。
[7] Stroe D.-I., Knap V., Swierczynski M., Stroe A.-I., Teodorescu R., " Operation of a grid-connected lithium-ion battery energy storage system for primary frequency regulation: A battery lifetime perspective" in IEEE Transactions on Industrial Electronics, vol. 53, no. 1, pp. 430-438, 2017.
[8] Zhang Y, Xiong R, He H, Qu X, Pecht M, "Aging characteristics-based health diagnosis and remaining useful life prognostics for lithium-ion batteries," eTransportation, vol. 1, pp. 100004, 2019.
[9] Yu J. " State of health prediction of lithium-ion batteries: Multiscale logic regression and Gaussian process regression ensemble," Reliability Engineering & System Safety, Vol. 174, pp. 82-95, 2018.
[10] Changki Choi, Seongyun Park, Jonghoon Kim, "Uniqueness of multilayer perceptron-based capacity prediction for contributing state-of-charge estimation in a lithium primary battery," Ain Shams Engineering Journal, Vol. 14, 2023.
[11] A. Basia, Z. Simeu-Abazi, E. Gascard and P. Zwolinski, "Comparison of data driven algorithms for SoH estimation of Lithium-ion batteries," International Conference on Control, Automation and Diagnosis (ICCAD), Grenoble, France, pp. 1-6, 2021.
[12] Li Y, Zou C, Berecibar M, Nanini-Maury E, Chan JCW, van den Bossche P, et al. " Random forest regression for online capacity estimation of lithium-ion batteries" Applied Energy, vol. 232, pp. 197-210, 2018.
[13] Plaia, A., Buscemi, S., Fürnkranz, J. et al. "omparing Boosting and Bagging for Decision Trees of Rankings." J Classif, Vol. 39, pp. 78-99, 2022.
[14] S. Pathak, I. Mishra and A. Swetapadma, "An Assessment of Decision Tree based Classification and Regression Algorithms," 2018 3rd International Conference on Inventive Computation Technologies (ICICT), pp. 82-95, 2018.
[15] Wei Zhu, Mei Xie and Jian-Feng Xie, "A decision tree algorithm for license plate recognition based on bagging," 2012 International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP), pp. 136-139, 2012.
[16] Z. Khan, N. Gul, N. Faiz, A. Gul, W. Adler and B. Lausen, "Optimal Trees Selection for Classification via Out-of-Bag Assessment and Sub-Bagging," in IEEE Access, Vol. 9, pp. 28591-28607, 2021.
[17] S. Shumaly, P. Neysaryan and Y. Guo, "Handling Class Imbalance in Customer Churn Prediction in Telecom Sector Using Sampling Techniques, Bagging and Boosting Trees," 2020 10th International Conference on Computer and Knowledge Engineering (ICCKE), pp. 82-87, 2020.
[18] Clifton D. Sutton, "Classification and Regression Trees, Bagging, and Boosting," Handbook of Statistics, vol. 24, pp. 303-329 , 2005.
[19] James, G., Witten, D., Hastie, T., Tibshirani, R., Taylor, J. "Tree-Based Methods. " In An Introduction to Statistical Learning, pp. 331-366, 2023 .
[20] Kadiyala, A., Kumar, A., "Applications of python to evaluate the performance of bagging methods. " American Institute of Chemical Engineers Environ, vol. 37, pp. 1555-1559, 2018.
[21] D. Ge and X. -J. Zeng, "Functional Fuzzy System: A Nonlinear Regression Model and Its Learning Algorithm for Function-on-Function Regression," in IEEE Transactions on Fuzzy Systems, vol. 30, pp. 956-967.
[22] Søren B. Vilsen, Daniel-Ioan Stroe, "Battery state-of-health modelling by multiple linear regression," Journal of Cleaner Production, vol. 290, 2021.
[23] Wu, Yc., Feng, Jw. "Development and Application of Artificial Neural Network. " Wireless Pers Commun vol. 102, pp. 1645–1656, 2018.
[24] D. N. T. How, M. A. Hannan, M. S. H. Lipu, K. S. M. Sahari, P. J. Ker and K. M. Muttaqi, "State-of-Charge Estimation of Li-Ion Battery in Electric Vehicles: A Deep Neural Network Approach," in IEEE Transactions on Industry Applications, vol. 56, no. 5, pp. 5565-5574, 2020
[25] X. Feng et al., "Online State-of-Health Estimation for Li-Ion Battery Using Partial Charging Segment Based on Support Vector Machine," in IEEE Transactions on Vehicular Technology, vol. 68, no. 9, pp. 8583-8592, 2019.
[26] J. Li, M. Ye, W. Meng, X. Xu and S. Jiao, "A Novel State of Charge Approach of Lithium Ion Battery Using Least Squares Support Vector Machine," in IEEE Access, vol. 8, pp. 195398-195410, 2020.
[27] Hodson, T. O. " Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not," Geosci. Model Dev. Vol. 15, pp. 5481-5487, 2022.
[28] Davide Chicco, Matthijs J. Warrens, Giuseppe Jurman, "The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation," Article in PeerJ Computer Science, 2021. DOI: https://doi.org/10.7717/peerj-cs.623