請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/73195完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 李綱(Kang Li) | |
| dc.contributor.author | Zheng-Jie Chen | en |
| dc.contributor.author | 陳正傑 | zh_TW |
| dc.date.accessioned | 2021-06-17T07:21:53Z | - |
| dc.date.available | 2019-07-15 | |
| dc.date.copyright | 2019-07-15 | |
| dc.date.issued | 2019 | |
| dc.date.submitted | 2019-07-03 | |
| dc.identifier.citation | [1] The IEA Energy Efficiency Indicators Database https://www.iea.org/newsroom/news/2017/december/the-iea-energy-efficiency-indicators-database.html
[2] Fotouhi, Abbas, et al. 'A review on the applications of driving data and traffic information for vehicles? energy conservation.' Renewable and Sustainable Energy Reviews 37 (2014): 822-833. [3] 周芳杰, '使用車載資通訊之電動車智慧節能行駛技術之研究',2013. [4] Yazdani, Arya, and Mehran Bidarvatan. A Comparative Analysis for Optimal Control of Power Split in a Fuel Cell Hybrid Electric Vehicle. No. 2016-01-1189. SAE Technical Paper, 2016. [5] 顏良喜, '運用車載資通訊技術之插電式混合動力電動車智慧化能量管理策略',2015. [6] 許博鈞, '插電式混合動力電動車之智慧節能巡航控制研究', 2016. [7] Bär, Tobias, et al. 'Anticipatory driving assistance for energy efficient driving.' 2011 IEEE Forum on Integrated and Sustainable Transportation Systems. IEEE, 2011. [8] Kamal, Md Abdus Samad, et al. 'Ecological vehicle control on roads with up-down slopes.' IEEE Transactions on Intelligent Transportation Systems 12.3 (2011): 783-794. [9] Kohut, Nicholas J., J. Karl Hedrick, and Francesco Borrelli. 'Integrating traffic data and model predictive control to improve fuel economy.' IFAC Proceedings Volumes 42.15 (2009): 155-160. [10] Kamal, Md Abdus Samad, et al. 'On board eco-driving system for varying road-traffic environments using model predictive control.' 2010 IEEE International Conference on Control Applications. IEEE, 2010. [11] Wang, Meng, et al. 'Driver assistance systems modeling by model predictive control.' Intelligent Transportation Systems (ITSC), 2012 15th International IEEE Conference on. IEEE, 2012. [12] Sakhdari, Bijan, Mahyar Vajedi, and Nasser L. Azad. 'Ecological adaptive cruise control of a plug-in hybrid electric vehicle for urban driving.' 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC). IEEE, 2016 [13] Vajedi, Mahyar, and Nasser L. Azad. 'Ecological adaptive cruise controller for plug-in hybrid electric vehicles using nonlinear model predictive control.' IEEE Transactions on Intelligent Transportation Systems 17.1 (2016): 113-122. [14] Jin, Qiu, et al. 'Power-based optimal longitudinal control for a connected eco-driving system.' IEEE Transactions on Intelligent Transportation Systems 17.10 (2016): 2900-2910. [15] Hoogendoorn, Serge, et al. 'Modeling driver, driver support, and cooperative systems with dynamic optimal control.' Transportation Research Record: Journal of the Transportation Research Board 2316 (2012): 20-30. [16] Tunnell, Jordan, et al. 'Toward Improving Vehicle Fuel Economy with ADAS.' SAE International Journal of Connected and Automated Vehicles 1.12-01-02-0005 (2018): 81-92. [17] Qi, Xuewei, et al. 'Deep reinforcement learning-based vehicle energy efficiency autonomous learning system.' 2017 IEEE Intelligent Vehicles Symposium (IV). IEEE, 2017. [18] Lin, Xue, et al. 'Reinforcement learning based power management for hybrid electric vehicles.' Proceedings of the 2014 IEEE/ACM International Conference on Computer-Aided Design. IEEE Press, 2014. [19] Liu, Teng, et al. 'Reinforcement learning optimized look-ahead energy management of a parallel hybrid electric vehicle.' IEEE/ASME Transactions on Mechatronics 22.4 (2017): 1497-1507. [20] Martinez, Clara Marina, et al. 'Driving style recognition for intelligent vehicle control and advanced driver assistance: A survey.' IEEE Transactions on Intelligent Transportation Systems19.3 (2018): 666-676. [21] Meseguer, Javier E., et al. 'Drivingstyles: a mobile platform for driving styles and fuel consumption characterization.' Journal of Communications and Networks 19.2 (2017): 162-168. [22] Lee, Taeyoung, and Joonwoo Son. Relationships between driving style and fuel consumption in highway driving. No. 2011-28-0051. SAE Technical Paper, 2011. [23] Rajan, Brahmadevan V. Padma, Andrew McGordon, and Paul A. Jennings. 'An investigation on the effect of driver style and driving events on energy demand of a PHEV.' World Electric Vehicle Journal 5.1 (2012): 173-181. [24] Eboli, Laura, Gabriella Mazzulla, and Giuseppe Pungillo. 'The influence of physical and emotional factors on driving style of car drivers: a survey design.' Travel Behaviour and Society 7 (2017): 43-51. [25] Corti, Andrea, et al. 'Quantitative driving style estimation for energy-oriented applications in road vehicles.' Systems, Man, and Cybernetics (SMC), 2013 IEEE International Conference on. IEEE, 2013. [26] Romera, Eduardo, Luis M. Bergasa, and Roberto Arroyo. 'Need data for driver behaviour analysis? Presenting the public UAH-DriveSet.' 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC). IEEE, 2016. [27] Vaitkus, Vygandas, Paulius Lengvenis, and Gediminas ?ylius. 'Driving style classification using long-term accelerometer information.' Methods and Models in Automation and Robotics (MMAR), 2014 19th International Conference On. IEEE, 2014. [28] Rosenfeld, Avi, et al. 'Learning drivers’ behavior to improve adaptive cruise control.' Journal of Intelligent Transportation Systems 19.1 (2015): 18-31. [29] Murphey, Yi Lu, Robert Milton, and Leonidas Kiliaris. 'Driver's style classification using jerk analysis.' Computational Intelligence in Vehicles and Vehicular Systems, 2009. CIVVS'09. IEEE Workshop on. IEEE, 2009. [30] Karginova, Nadezda, Stefan Byttner, and Magnus Svensson. Data-driven methods for classification of driving styles in buses. No. 2012-01-0744. SAE Technical Paper, 2012. [31] Dörr, Dominik, David Grabengiesser, and Frank Gauterin. 'Online driving style recognition using fuzzy logic.' Intelligent Transportation Systems (ITSC), 2014 IEEE 17th International Conference on. IEEE, 2014. [32] Brombacher, Patrick, et al. 'Driving event detection and driving style classification using artificial neural networks.' Industrial Technology (ICIT), 2017 IEEE International Conference on. IEEE, 2017. [33] Meseguer, Javier E., et al. 'Drivingstyles: A smartphone application to assess driver behavior.' Computers and Communications (ISCC), 2013 IEEE Symposium on. IEEE, 2013. [34] Bolovinou, Anastasia, et al. 'Driving style recognition for co-operative driving: A survey.' The Sixth International Conference on Adaptive and Self-Adaptive Systems and Applications. 2014. [35] Augustynowicz, A. N. D. R. Z. E. J. 'Preliminary classification of driving style with objective rank method.' International journal of automotive technology 10.5 (2009): 607-610. [36] Saleh, Khaled, Mohammed Hossny, and Saeid Nahavandi. 'Driving behavior classification based on sensor data fusion using LSTM recurrent neural networks.' 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC). IEEE, 2017. [37] Dong, Weishan, et al. 'Characterizing driving styles with deep learning.' arXiv preprint arXiv:1607.03611 (2016). [38] Milesich, Tomáš, Ján Danko, and Jozef Bucha. 'Neural Networks-A Way to Increase the Fuel Efficiency of Vehicles.' Strojnícky casopis–Journal of Mechanical Engineering 68.1 (2018): 81-88. [39] Wang, Rui, and Srdjan M. Lukic. 'Review of driving conditions prediction and driving style recognition based control algorithms for hybrid electric vehicles.' Vehicle Power and Propulsion Conference (VPPC), 2011 IEEE. IEEE, 2011. [40] Ohn-Bar, Eshed, et al. 'Head, eye, and hand patterns for driver activity recognition.' Pattern Recognition (ICPR), 2014 22nd International Conference on. IEEE, 2014. [41] Wang, Wenshuo, and Junqiang Xi. 'A rapid pattern-recognition method for driving styles using clustering-based support vector machines.' American Control Conference (ACC), 2016. IEEE, 2016. [42] R. Rajamani, Vehicle Dynamics and Control: Springer US, 2005 [43] Machine Learning, Tom M. Mitchell, McGraw Hill, 1997. [44] Møller, Martin Fodslette. 'A scaled conjugate gradient algorithm for fast supervised learning.' Neural networks 6.4 (1993): 525-533. [45] Graves, Alex. 'Supervised sequence labelling with recurrent neural networks. 2012.' [46] Hochreiter, Sepp, and Jürgen Schmidhuber. 'Long short-term memory.' Neural computation 9.8 (1997): 1735-1780. [47] Guo, Jiang. 'Backpropagation through time.' Unpubl. ms., Harbin Institute of Technology (2013). [48] Kingma, Diederik P., and Jimmy Ba. 'Adam: A method for stochastic optimization.' arXiv preprint arXiv:1412.6980 (2014). [49] Rumelhart, David E., Geoffrey E. Hinton, and Ronald J. Williams. 'Learning representations by back-propagating errors.' Cognitive modeling 5.3 (1988): 1. [50] Tieleman, Tijmen, and Geoffrey Hinton. 'Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude.' COURSERA: Neural networks for machine learning 4.2 (2012): 26-31. [51] L. Wang, Model predictive control system design and implementation using MATLAB®: Springer Science & Business Media, 2009. [52] Camacho, Eduardo F., and Carlos Bordons. 'Nonlinear model predictive control: An introductory review.' Assessment and future directions of nonlinear model predictive control. Springer, Berlin, Heidelberg, 2007. 1-16. [53] Bellman, Richard E., and Stuart E. Dreyfus. Applied dynamic programming. Vol. 2050. Princeton university press, 2015. [54] H. A. Rakha, K. Ahn, K. Moran, B. Saerens, and E. Van den Bulck, 'Virginia tech comprehensive power-based fuel consumption model: model development and testing,' Transportation Research Part D: Transport and Environment, vol. 16, pp. 492-503, 2011. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/73195 | - |
| dc.description.abstract | 本研究結合類神經網絡及模型預測控制，開發智慧節能行車輔助控制架構，並運用車載資通訊及監督式學習，提升車輛之行駛效能，以達到智慧節能行駛之目的。首先，模型預測控制會根據車輛動態、道路參數與前方交通動態資訊等，調整最佳車速及馬達力矩，使動力系統運作於高效區。駕駛者風格則透過監督式學習進行分類，分類器採用深度神經網絡(Deep Neural Networks, DNN)與循環神經網絡(Recurrent Neural Network, RNN)兩種模型，透過先前駕駛者資訊以及車輛動態資訊，進行駕駛者風格分類，模擬結果證明此兩種方法皆具有90%之準確度。最後，車輛控制單元會根據駕駛者風格、最佳扭矩與駕駛者控制訊號，進行車輛節能之介入控制。此外，透過駕駛者於模擬環境中(Driver-in-the-Loop, DiL)之模擬結果顯示，運用此套智慧節能行車輔助架構，在高速公路情境下，可減少8~10%之行車能耗。 | zh_TW |
| dc.description.abstract | This research combines neural network and model predictive control to develop intelligent eco-driving assistance control architecture, Using telematics and supervised learning improve the driving performance of vehicles in order to achieve the goal of intelligent eco-driving. First, the model predictive control adjusts the optimal speed and motor torque according to the vehicle dynamics, road parameters and traffic dynamics information in front, the powertrain system can then be adjusted to the corresponding high efficiency zone. Individual driving style is then classified by supervised learning algorithm; The classifier uses two models: Deep Neural Networks (DNN) and Recurrent Neural Network (RNN). The classifier collects past driver and vehicle dynamic information for driver style classification, with simulation results demonstrating 90% accuracy for both classifiers on driving style differentiation. Finally, the vehicle control unit performs interventional control based on driver style, optimal torque and driver control signals. In addition, through the simulation results of the driver in the simulated environment (driver in the loop, DiL), the intelligent eco-driving assistance control architecture can reduce the energy consumption by 8-10% in the highway situation. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T07:21:53Z (GMT). No. of bitstreams: 1 ntu-108-R05522833-1.pdf: 7277251 bytes, checksum: 4e052dc7ba12baacb41ca95563f1050a (MD5) Previous issue date: 2019 | en |
| dc.description.tableofcontents | 目錄
摘要 I Abstract II 目錄 III 圖目錄 V 表目錄 VIII 符號表 IX 縮寫對照表 XI 第一章 緒論 1 1.1 研究動機與目的 1 1.2 文獻回顧 2 1.3 研究貢獻 8 第二章 系統架構與模組設計 9 2.1 系統架構 9 2.2 資料傳輸 11 2.3 機器學習(Machine Learning, ML) 11 2.3.1 機器學習種類 13 2.3.2 機器學習步驟 14 2.3.3 人工神經網絡(Artificial Neural Network，ANN) 14 2.3.4 評估模型驗證指標(Validation Index) 33 2.4 最佳化單元 37 2.4.1 模型預測控制器[51] 38 2.4.2 系統模型 41 2.4.3 成本函數 43 2.4.4 限制條件 44 2.4.5 最佳化-動態規劃法 45 2.5 車輛控制單元 51 第三章 模擬結果分析與討論 52 3.1 模擬架構與環境介紹 52 3.2 複合動力系統架構 58 3.3 系統模型 59 3.3.1 車輛縱向模型 59 3.3.2 前軸引擎模型 61 3.3.3 前軸馬達模型 63 3.3.4 後軸馬達模型 65 3.3.5 減速齒輪箱模型 66 3.4 不同分類器架構比較 67 3.4.1 參數選用 67 3.4.2 DNN 架構設定與結果分析 67 3.4.3 RNN 架構設定與結果分析 73 3.4.4 神經網絡模型結果比較 77 3.5 不同參數差異分析與比較 78 3.5.1 成本函數不同權重差異分析 78 3.5.2 不同上下限車速差異分析 87 3.5.3 不同更新頻率差異 90 3.6 整體控制系統模擬結果 91 第四章 結論與未來工作建議 98 4.1 結論 98 4.2 未來工作建議 99 參考文獻 100 圖目錄 圖 1 1、影響駕駛風格之因素 5 圖 2 1、智慧節能行車輔助架構 10 圖 2 2、分類器輸出輸入示意圖 12 圖 2 3、機械學習分類 12 圖 2 4、機械學習步驟 14 圖 2 5、人工神經元 15 圖 2 6、神經網絡典型架構 16 圖 2 7、前向傳播詳細圖 17 圖 2 8、反向傳播過程 21 圖 2 9、不同學習率之影響 22 圖 2 10、循環神經網絡架構 23 圖 2 11、依據不同輸入與輸出進行分類 24 圖 2 12、Recurrent Neural Network架構 25 圖 2 13、Long Short-Term Memory Cell架構 26 圖 2 14、LSTM反向傳播示意圖 28 圖 2 15、混淆矩陣 33 圖 2 16、混淆矩陣多種指標 34 圖 2 17、ROC曲線 36 圖 2 18、三種不同AUC值(曲線下面積) 36 圖 2 19、模型預測控制系統架構[52] 40 圖 2 20、路徑與成本圖 46 圖 2 21、最佳路徑與成本圖 46 圖 2 22、以距離離散化最佳化問題 47 圖 3 1、Matlab/Simulink控制演算法架構 52 圖 3 2、模擬道路距離與高度 53 圖 3 3、模擬道路距離與坡度 54 圖 3 4、模擬環境 54 圖 3 5、資料收集架構圖 55 圖 3 6、駕駛模擬器硬體架構圖 55 圖 3 7、駕駛模擬器Logitech G29 55 圖 3 8、實際硬體圖 57 圖 3 9、複合動力系統架構(EVX5) 58 圖 3 10、車輛座標示意圖 59 圖 3 11、引擎模型示意圖 61 圖 3 12、引擎燃油效率圖 62 圖 3 13、馬達模型示意圖 63 圖 3 14、特徵數量為1之混淆矩陣 69 圖 3 15、特徵數量為1之ROC曲線 69 圖 3 16、特徵數量為2之混淆矩陣 70 圖 3 17、特徵數量為2之ROC曲線 70 圖 3 18、特徵數量為3之混淆矩陣 71 圖 3 19、特徵數量為3之ROC曲線 71 圖 3 20、特徵數量為6之混淆矩陣 72 圖 3 21、特徵數量為6之ROC曲線 72 圖 3 22、特徵數量為1之訓練過程 75 圖 3 23、特徵數量為2之訓練過程 75 圖 3 24、特徵數量為3之訓練過程 75 圖 3 25、特徵數量為6之訓練過程 76 圖 3 26、模擬道路高度圖 78 圖 3 27、平均車流速 79 圖 3 28、前車車速速度曲線圖 79 圖 3 29、不同w0對車速之影響 81 圖 3 30、不同w0對能耗之影響 81 圖 3 31、不同w1對車速之影響 82 圖 3 32、不同w1對能耗之影響 82 圖 3 33、不同w2對車速之影響 83 圖 3 34、不同w2對能耗之影響 83 圖 3 35、不同w3對車速之影響 84 圖 3 36、不同w3與前車之相對距離 84 圖 3 37、不同w3對能耗之影響 85 圖 3 38、不同w4對車速之影響 85 圖 3 39、不同w4與前車之相對距離 86 圖 3 40、不同w4對能耗之影響 86 圖 3 41、模擬道路高度圖 88 圖 3 42、不同調變區間之速度變化 88 圖 3 43、不同調變區間之能耗變化 89 圖 3 44、道路高度圖 91 圖 3 45、平均車流速 91 圖 3 46、前車車速圖 92 圖 3 47、50筆駕駛者時間與能耗關係圖 93 圖 3 48、MPC計算出最佳車速圖 93 圖 3 49、透過控制器一之駕駛者能耗與時間圖 95 圖 3 50、原始資料與控制器一之駕駛者能耗與時間關係圖 95 圖 3 51、透過控制器二之駕駛者能耗與時間圖 96 圖 3 52、原始資料與控制器二之駕駛者能耗與時間關係圖 96 圖 3 53、原始資料與兩控制器之駕駛者能耗與時間關係圖 97 表目錄 表格 3 1、車輛參數表 53 表格 3 2、方向盤、踏板、變速器尺寸 56 表格 3 3、方向盤規格 56 表格 3 4、踏板規格 56 表格 3 5、引擎最大力矩限制表 62 表格 3 6、前軸馬達規格表 63 表格 3 7、前軸馬達最大力矩限制表 64 表格 3 8、後軸馬達最大力矩限制表 65 表格 3 9、各部件齒輪比 66 表格 3 10、不同輸入資料 68 表格 3 11、不同輸入下DNN模型之訓練效果 73 表格 3 12、不同資料量下DNN模型訓練效果 73 表格 3 13、不同輸入資料 74 表格 3 14、不同輸入下RNN模型之訓練效果 76 表格 3 15、不同資料量下RNN模型訓練效果 76 表格 3 16、不同調變區間之能耗與時間差異 89 表格 3 17、不同更新頻率差異 90 表格 3 18、不同控制器之權重值 94 表格 3 19、控制結果綜合比較 97 | |
| dc.language.iso | zh-TW | |
| dc.title | 結合類神經網絡及模型預測控制之智慧節能行車輔助系統 | zh_TW |
| dc.title | Intelligent eco-driving assistance system through combination of neural network and model predictive control | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 107-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 林峻永(Chun-Yeon Lin),顏家鈺(Jia-Yush Yen) | |
| dc.subject.keyword | 駕駛者風格分類,模型預測控制,監督式學習,駕駛輔助系統,智慧運輸系統, | zh_TW |
| dc.subject.keyword | Driver style classification,Model predictive control,Supervise learning,Driver assistance system,Intelligent transportation systems, | en |
| dc.relation.page | 104 | |
| dc.identifier.doi | 10.6342/NTU201900950 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2019-07-04 | |
| dc.contributor.author-college | 工學院 | zh_TW |
| dc.contributor.author-dept | 機械工程學研究所 | zh_TW |
| 顯示於系所單位： | 機械工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-108-1.pdf 目前未授權公開取用 | 7.11 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。