跳到主要內容

臺灣博碩士論文加值系統

(44.211.31.134) 您好!臺灣時間:2024/07/24 17:26
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:王贊棠
研究生(外文):Zan-Tang Wang
論文名稱:利用服役數據和機器學習模型評估混合動力汽車鎳氫電池的健康狀態
論文名稱(外文):State of health estimation of nickel metal hybrid batteries for hybrid electric vehicles with on-road service data and machine learning models
指導教授:陳洵毅
指導教授(外文):Hsun-Yi Chen
口試委員:周呈霙陳倩瑜郭錦龍
口試委員(外文):Cheng-Ying ChouChien-Yu ChenChin-Lung Guo
口試日期:2024-01-29
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:生物機電工程學系
學門:工程學門
學類:機械工程學類
論文種類:學術論文
論文出版年:2024
畢業學年度:112
語文別:中文
論文頁數:122
中文關鍵詞:鎳氫電池電池健康狀態機器學習老化實驗遷移學習
外文關鍵詞:NiMHSOHmachine learningaging experimenttransfer learning
DOI:10.6342/NTU202400743
相關次數:
  • 被引用被引用:0
  • 點閱點閱:21
  • 評分評分:
  • 下載下載:9
  • 收藏至我的研究室書目清單書目收藏:0
隨著全球氣侯變遷加劇及環保意識抬頭,油電混合車及電動車的銷量與日俱增,其中油電混合車於上世紀末商業化,至今已有逾千萬台的油電車於全球運行;而鎳氫電池作為其主要的儲電元件,未來全球將有大量的汰役電池需要被妥善處理。過往處理電池需要對電池做完全充放電,知道電池實際的充放電能力後,再依照量測結果判斷電池是否適合繼續服役,抑或是廢棄淘汰,但是完全充放電時間太長,不利於應付未來龐大的電池回收潮。此外也希望能夠預測電池性能未來的使用狀況和變化程度,依照電池老化狀況安排合適的使用方式,延長服役時間以節省製造電池的成本和資源,為此我們急需快速且準確的手段,檢測電池實際性能並進階地預測到未來的電池狀態變化。
由於科技的普及與資料科學之快速進展,人工智慧(artificial intelligence, AI)已經被應用於許多產業以增進生產效率和社會福祉。過去已有文獻將其應用於預測電池之健康狀態(state of health, SOH),能準確地甄別電池狀態並取得優秀的成效,但是訓練樣本通常不大,僅限於幾百甚至幾十個,樣本數過小可能導致訓練出現偏差;再者,文獻中的電池大多是處於實驗室特定參數設置下規律地操作,與大多數上路電池經歷的操作歷程相當不同,訓練出的模型是否能處理使用歷程複雜的電池值得懷疑;最後,大部分的文獻關注探討鋰電池的性能和應用,近年少有針對鎳氫電池之健康狀態的預測和研究。但參考市場機構的調查,鎳氫電池以其突出的安全性依舊能在新能源交通工具中扮演重大的角色,因此發展出一套系統性判斷電池健康狀態,以利廠商分級回收再利用是很重要的事情。
我們也將應用人工智慧進行本研究。首先,我們透過詳盡的鎳氫電池文獻回顧,了解鎳氫電池的運作機制和衰退成因,以及其健康狀態的定義及量測方法,決定用恆流充放電(galvanostatic charge/discharge, GCD)檢測電池性能。我們認為充電曲線對電池性能高度相關,並據此設計並選擇了5個特徵。之後,歸納常見的機器學習模型並選擇貝葉斯山脊型迴歸(Bayesian ridge regression, BRR)、前饋神經網路(feedforward neural network, FNN)和隨機森林(Random forest, RF)進行訓練、測試,以很小的誤差準確預測電池之性能。為了確認特徵的泛化性能(generalizability),我們執行了兩組老化實驗,驗證選擇的特徵在不同環境下產生的數據上依然適用,最後輔以遷移學習(transfer learning),縮小不同數據中特徵的差異,進一步地縮小預測誤差。
Along with the aggravating climate change and rising environmental awareness, sales of hybrid electric vehicles (HEVs) and electric vehicles (EVs) are increasing. The HEVs in particular, are commercialized by the end of last century and more than 10 million of them are operating around the world. Since nickel metal hydride (NiMH) batteries are the core energy storage component on board of HEVs, a significant amount of retired NiMH batteries will flood the world, requiring proper treatment. In the past, battery testing required a complete charge and discharge process to measure the actual charging and discharging capacity of the battery, and determine theirs application, to be on service or be discarded afterward. However, the complete charge and discharge process is time-consuming, not suitable for dealing with the upcoming massive battery recycling wave. Additionally, there is a desire to predict the future usage conditions and changes in battery performance, based on the battery's aging status, to arrange appropriate usage methods and extend the service life to save the cost and resources of battery manufacturing. Therefore, a fast and accurate method to obtain the actual performance of batteries and predict their future state changes is desired.
Due to the popularization of technology and rapid advancements in data science, artificial intelligence (AI) has been applied in various industries to improve production efficiency and social welfare. Previous studies have applied AI to predict the state of health (SOH) of batteries, achieving accurate identification of battery conditions and excellent results. However, the training samples are usually small, a few hundreds or even dozens. The small sample size may lead to bias in training. Moreover, the batteries in the literature are mostly operated under specific laboratory parameters, which are quite different from those on-road batteries, doubtful whether the trained models can handle batteries with complex usage history. Lastly, most of the literature focuses on the performance and application of lithium batteries, with limited research on the prediction of the state of health of nickel-hydrogen batteries, which is however, still play a significant role in new energy vehicles due to their outstanding safety. Therefore, it is important to develop a systematic approach to assess the health status of batteries, allowing manufacturers to classify and recycle them for reuse.
We also applied AI techniques in this study. Firstly, through a comprehensive literature review on NiMH, we gained an understanding of their operating mechanisms, degradation factors, and the definition and measurement methods of their SOH. We used galvanostatic charge/discharge (GCD) to assess battery performance. Recognizing the high correlation between charge curves and battery performance, we designed and selected five features. Subsequently, we summarized common machine learning models and chose Bayesian ridge regression (BRR), feedforward neural network (FNN), and random forest (RF) for training and testing. These models accurately predict battery performance with minimal errors. To confirm the generalizability of features, we conducted two aging experiments, validating that the selected features remain applicable in different environments. Finally, employing transfer learning helped narrow feature differences across various datasets, further reducing prediction errors
致謝 i
摘要 ii
Abstract iv
目次 vi
圖次 viii
表次 x
第一章 研究目的 1
第二章 文獻探討 3
2.1 鎳氫電池的充電曲線和化學反應 3
2.2 鎳氫電池性能與容量衰退成因 5
2.3 充電曲線上的特徵 7
2.3.1 反曲點 7
2.3.2 弛豫現象 7
2.3.3 其他特徵變數 9
2.4 性能狀態指標 10
2.5 SOH預測方法文獻回顧 13
2.6機器學習法(ML) 14
2.7 加速老化實驗 20
2.8 遷移學習 21
2.9 研究缺口與文獻回顧總結 24
第三章 研究材料和方法 25
3.1 研究架構與流程 25
3.2 實驗方法和數據 26
3.3 反曲點分析 32
3.4 弛豫現象 35
3.5 其他特徵變數 36
3.6 建立機器學習模型 38
3.7 衡量機器學習模型成效 41
3.8 遷移學習 43
3.9 作業流程 44
第四章 結果 45
4.1 特徵工程 45
4.2 機器學習模型 48
4.2.1 網格搜尋的結果 48
4.2.2 模型成效 50
4.3 特徵重要性 54
4.4 老化數據視覺化 60
4.5 遷移學習效果 62
4.5.1 數據集和特徵分布 62
4.5.2 測試結果 66
4.6 完整流程圖 70
第五章 總結 72
第六章 未來工作 74
參考文獻 75
附錄 81
A.1 讀取服役數據、高溫老化數據,提取特徵的程式碼 81
A.2 讀取高速老化數據、提取特徵的程式碼 87
A.3 找出合適的弛豫時間的程式碼 92
A.4 找出缺失值、異常值的程式碼 93
A.5 進行機器學習之前,進行數據清理 95
A.6 BRR、RF、FNN程式碼 96
A.7 畫ML你和曲線圖、殘差分布圖、殘差百分比分布圖的程式碼 100
A.8 MMD的程式碼以及進行遷移學習的流程 102
A9 對隨機森林演算法做Gridsearch的結果 109
A10 對前饋神經網路做Gridsearch的結果 115
汤依伟, 艾亮, 程昀, 王安安, 李书国 and 贾明 (2015). "锂离子动力电池高倍率充放电过程中弛豫行为的仿真." 物理学报 64(24): 248201.
张志刚, 张涛, 汤爱华, 姚疆 and 蒋依汗 (2022). "车用锂电池健康状态下快充方法研究综述." 西南大学学报 (自然科学版) 44(2): 194-206
Aminzadegan, S., Shahriari, M., Mehranfar, F., & Abramović, B. (2022). Factors affecting the emission of pollutants in different types of transportation: A literature review. Energy Reports, 8, 2508-2529.
Bornatico, R., A. Storti, L. Mandrioli, A. Zappavigna, Y. Guezennec and G. Rizzoni (2007). NiMH battery characterization and state-of-charge estimation for HEV applications. ASME International Mechanical Engineering Congress and Exposition.
Chen, W., Z. Xu and J. Tu (2002). "Electrochemical investigations of activation and degradation of hydrogen storage alloy electrodes in sealed Ni/MH battery." International journal of hydrogen energy 27(4): 439-444.
Chen, X., A. Chu, D. Li, Y. Yuan, X. Fan and Y. Deng (2021). "Development of the cycling life model of Ni-MH power batteries for hybrid electric vehicles based on real-world operating conditions." Journal of Energy Storage 34: 101999.
Chen, Y., L. Yang, F. Guo, D. Liu, H. Wang, J. Lu, J. Zheng, X. Yu and H. Li (2022). "Mechanical-electrochemical modeling of silicon-graphite composite anode for lithium-ion batteries." Journal of Power Sources 527: 231178.
Chehab, Z., L. Serrao, Y. G. Guezennec and G. Rizzoni (2006). Aging Characterization of Nickel: Metal Hydride Batteries Using Electrochemical Impedance Spectroscopy. ASME International Mechanical Engineering Congress and Exposition.
Cheng, S., J. Zhang, H. Liu, Y. Leng, A. Yuan and C. Cao (1998). "Study of early cycling deterioration of a Ni/MH battery by electrochemical impedance spectroscopy." Journal of power sources 74(1): 155-157.
Cui, Z., L. Wang, Q. Li and K. Wang (2022). "A comprehensive review on the state of charge estimation for lithium‐ion battery based on neural network." International Journal of Energy Research 46(5): 5423-5440.
Fetcenko, M., J. Koch and M. Zelinsky (2015). Nickel–metal hydride and nickel–zinc batteries for hybrid electric vehicles and battery electric vehicles. Advances in battery technologies for electric vehicles, Elsevier: 103-126.
Galeotti, M., C. Giammanco, L. Cinà, S. Cordiner and A. Di Carlo (2015). "Synthetic methods for the evaluation of the State of Health (SOH) of nickel-metal hydride (NiMH) batteries." Energy conversion and management 92: 1-9.
Gao, D., M. Huang and J. Xie (2017). "A novel indirect health indicator extraction based on charging data for lithium-ion batteries remaining useful life prognostics." SAE International Journal of Alternative Powertrains 6(2): 183-193.
Han, T., et al. (2022). "End-to-end capacity estimation of Lithium-ion batteries with an enhanced long short-term memory network considering domain adaptation." Journal of Power Sources 520: 230823.
Hosen, M. S., R. Youssef, T. Kalogiannis, J. Van Mierlo and M. Berecibar (2021). "Battery cycle life study through relaxation and forecasting the lifetime via machine learning." Journal of Energy Storage 40: 102726.
Hu, X., et al. (2015). "Battery health prognosis for electric vehicles using sample entropy and sparse Bayesian predictive modeling." IEEE Transactions on Industrial Electronics 63(4): 2645-2656.
Jafari, S., et al. (2022). "Lithium-Ion Battery Health Prediction on Hybrid Vehicles Using Machine Learning Approach." Energies 15(13): 4753.)
Jones, R. and W. Reoch (1985). Charging system for nickel-zing batteries.
Kasnatscheew, J., T. Placke, B. Streipert, S. Rothermel, R. Wagner, P. Meister, I. C. Laskovic and M. Winter (2017). "A tutorial into practical capacity and mass balancing of lithium ion batteries." Journal of the electrochemical society 164(12): A2479.
Khaleghi, S., D. Karimi, S. H. Beheshti, M. S. Hosen, H. Behi, M. Berecibar and J. Van Mierlo (2021). "Online health diagnosis of lithium-ion batteries based on nonlinear autoregressive neural network." Applied Energy 282: 116159.
Khaleghi, S., M. S. Hosen, D. Karimi, H. Behi, S. H. Beheshti, J. Van Mierlo and M. Berecibar (2022). "Developing an online data-driven approach for prognostics and health management of lithium-ion batteries." Applied Energy 308: 118348.
Kheirkhah-Rad, E. and M. Moeini-Aghtaie (2021). A novel data-driven SOH prediction model for lithium-ion batteries. 2021 31st Australasian Universities Power Engineering Conference (AUPEC), IEEE.
Kim, C.-S., K. M. Jeong, K. Kim and C.-W. Yi (2015). "Effects of capacity ratios between anode and cathode on electrochemical properties for lithium polymer batteries." Electrochimica Acta 155: 431-436.
Kim, S., et al. (2021). "Forecasting state-of-health of lithium-ion batteries using variational long short-term memory with transfer learning." Journal of Energy Storage 41: 102893.
Le Guenne, L. and P. Bernard (2002). "Life duration of Ni–MH cells for high power applications." Journal of power sources 105(2): 134-138.
Li, W., et al. (2021). "Online capacity estimation of lithium-ion batteries with deep long short-term memory networks." Journal of Power Sources 482: 228863.
Luo, Y.-F. and K.-Y. Lu (2022). "An online state of health estimation technique for lithium-ion battery using artificial neural network and linear interpolation." Journal of Energy Storage 52: 105062.
Ma, G., et al. (2022). "A transfer learning-based method for personalized state of health estimation of lithium-ion batteries." IEEE Transactions on Neural Networks and Learning Systems.
Micea, M. V., et al. (2011). "Online State-of-Health Assessment for Battery Management Systems." Ieee Transactions on Instrumentation and Measurement 60(6): 1997-2006.
Minjie, Y. A. N. G., Junmin, N. A. N., Xianlu, H. O. U., & Weishan, L. I. (2008). Preparation and Electrochemical Performances of Nickel Metal Hydride Batteries with High Specific Volume Capacity. Chinese Journal of Chemical Engineering, 16(6), 944-948.
Mohammadi, F., & Saif, M. (2023). A Comprehensive Overview of Electric Vehicle Batteries Market. e-Prime-Advances in Electrical Engineering, Electronics and Energy, 100127.
Mu, G., S. Agrawal, P. Sittisomwong and P. Bai (2022). "Impacts of negative to positive capacities ratios on the performance of next-generation lithium-ion batteries." Electrochimica Acta 406: 139878.
Nicolai, J. and L. Wuidart (1995). From nickel-cadmium to nickel-hybride fast battery charger. Proceedings of 1995 International Conference on Power Electronics and Drive Systems. PEDS 95, IEEE.
Ng, M.-F., J. Zhao, Q. Yan, G. J. Conduit and Z. W. Seh (2020). "Predicting the state of charge and health of batteries using data-driven machine learning." Nature Machine Intelligence 2(3): 161-170.
Noura, N., L. Boulon and S. Jemeï (2020). "A review of battery state of health estimation methods: Hybrid electric vehicle challenges." World Electric Vehicle Journal 11(4): 66.
Park, S.-Y., H. Miwa, B. T. Clark, D. S. Ditzler, G. Malone, N. S. D'souza and J.-S. Lai (2008). A universal battery charging algorithm for Ni-Cd, Ni-MH, SLA, and Li-Ion for wide range voltage in portable applications. 2008 IEEE Power Electronics Specialists Conference, IEEE.
Paxton, B. and J. Newman (1997). "Modeling of nickel/metal hydride batteries." Journal of the Electrochemical Society 144(11): 3818.
Pradhan, S. K. and B. Chakraborty (2022). "Battery management strategies: An essential review for battery state of health monitoring techniques." Journal of Energy Storage 51: 104427.
Roman, D., S. Saxena, V. Robu, M. Pecht and D. Flynn (2021). "Machine learning pipeline for battery state-of-health estimation." Nature Machine Intelligence 3(5): 447-456.
Sahoo, S., et al. (2022). "Transfer learning based generalized framework for state of health estimation of Li-ion cells." Scientific Reports 12(1): 13173.
Sastry, A., S. Choi and X. Cheng (1998). "Damage in composite NiMH positive electrodes."
Schneider, E., C. Oliveira, R. Brito and C. Malfatti (2014). "Classification of discarded NiMH and Li-Ion batteries and reuse of the cells still in operational conditions in prototypes." Journal of Power Sources 262: 1-9.
Semanjski, I. and S. Gautama (2016). "Forecasting the state of health of electric vehicle batteries to evaluate the viability of car sharing practices." Energies 9(12): 1025.
Shen, L., Li, J., Meng, L., Zhu, L., & Shen, H. T. (2023). Transfer Learning-based State of Charge and State of Health Estimation for Li-ion Batteries: A Review. IEEE Transactions on Transportation Electrification.
Shu, X., et al. (2021). "A flexible state-of-health prediction scheme for lithium-ion battery packs with long short-term memory network and transfer learning." IEEE Transactions on Transportation Electrification 7(4): 2238-2248.
Shukla, A., S. Venugopalan and B. Hariprakash (2001). "Nickel-based rechargeable batteries." Journal of Power Sources 100(1-2): 125-148.
Su, S., et al. (2022). "A hybrid battery equivalent circuit model, deep learning, and transfer learning for battery state monitoring." IEEE Transactions on Transportation Electrification 9(1): 1113-1127.
Telmoudi, A. J., et al. (2020). "Modeling and state of health estimation of nickel-metal hydride battery using an EPSO-based fuzzy c-regression model." Soft Computing 24(10): 7265-7279.
Vidal, C., P. Malysz, P. Kollmeyer and A. Emadi (2020). "Machine learning applied to electrified vehicle battery state of charge and state of health estimation: State-of-the-art." IEEE Access 8: 52796-52814.
Xuan, D.-J., Z. Shi, J. Chen, C. Zhang and Y.-X. Wang (2020). "Real-time estimation of state-of-charge in lithium-ion batteries using improved central difference transform method." Journal of Cleaner Production 252: 119787.
Xue, Y., et al. (2022). Battery Degradation Modelling and Prediction with Combination of Machine Learning and Semi-empirical Methods. 2022 12th International Conference on Power, Energy and Electrical Engineering (CPEEE), IEEE.
Yang, H., Y. Qiu and X. Guo (2015). "Prediction of state-of-health for nickel-metal hydride batteries by a curve model based on charge-discharge tests." Energies 8(11): 12474-12487.
Yao, L., et al. (2022). "State of Health Estimation Based on the Long Short-Term Memory Network Using Incremental Capacity and Transfer Learning." Sensors 22(20): 7835.
Young, K.-h. and S. Yasuoka (2016). "Capacity degradation mechanisms in nickel/metal hydride batteries." Batteries 2(1): 3.
Young, K., T. Ouchi, W. Mays, B. Reichman and M. Fetcenko (2009). "Pressure–composition–temperature hysteresis in C14 Laves phase alloys: Part 2. Applications in NiMH batteries." Journal of alloys and compounds 480(2): 434-439.
Young, K., D. Wong, S. Yasuoka, J. Ishida, J. Nei and J. Koch (2014). "Different failure modes for V-containing and V-free AB2 metal hydride alloys." Journal of Power Sources 251: 170-177.
Zhang, Q., X. Li, Z. Du and Q. Liao (2021). "Aging performance characterization and state-of-health assessment of retired lithium-ion battery modules." Journal of Energy Storage 40: 102743.
Zhang, Y., et al. (2022). "A machine learning-based framework for online prediction of battery ageing trajectory and lifetime using histogram data." Journal of Power Sources 526: 231110.
Zhu, D., W. Zhou, Z. Tang, Y. Heng, K. Liu, J. Li, L. Xie and Y. Chen (2019). "SOC-dependent high-rate dischargeability of AB5-type metal hydride anode: Mechanism linking phase transition to electrochemical H-desorption kinetics." International Journal of Hydrogen Energy 44(29): 15278-15286.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊