臺灣博碩士論文加值系統

隨著無人車的發展趨勢，所使用的感測器和車用電子單元越來越多，搭配機器學習和AI控制已經是未來發展的重點項目。而因為車載網路變得更加複雜，導致現有CAN網路的頻寬使用接近技術限制。因此，Bosch公司於2012年推出了CAN FD協定。CAN FD繼承了CAN的主要特性，因此研究混合CAN和CAN FD網路非常重要。在本研究中以ECU sim2000 OBD-II模擬器，模擬真實汽車中的ECU，並透過自行設計的CAN FD/CAN閘道器，建置出以LPC54618微控制器實作4個CAN FD ECU，分別為引擎轉速、車輛速度、引擎冷卻劑溫度與含氧感知器電壓，同時設計以實現混和CAN和CAN FD網路，且透過VEDIS II手持式車輛連線診斷系統(Autoland Scientech公司)做為本研究系統驗證。
為了提高CAN FD網路的訊息可靠性。本研究提出了一種用於CAN FD之機器學習K-means資料分群法。在K-means中，使用歐幾里得平方距離與絕對誤差和，這兩種方法作為CAN FD的資料分群方法比較，且針對分群後的結果改變CAN FD ID，賦予CAN FD訊息不同優先權，並使PCAN-USB Pro FD(PEAK System)模擬測試。而透過這樣分群改變資料優先權的方法，本研究以資料遺失率作為改善的依據。
最後，經過本研究的整合測試，證明這樣的設計不僅能夠相容於目前CAN車載網路，且經過實驗，驗證K-means中，兩種算法處理六種不同資料量的CAN FD訊息分群後，可根據分群結果來改變CAN FD訊息的優先權順序，能有效的降低CAN FD網路的資料遺失率。其中，在CAN FD仲裁段速率同為1Mbps及資料段分別為2Mbps與4Mbps下，歐幾里得平方距離方法的資料遺失率降低了2.86%與2.58%；絕對誤差和方法的資料遺失率降低了2.66%與2.59%。換言之，兩種方法對於日漸複雜的車載網路來說，都提供更好的資訊可靠性以及安全性。

With the development trend of unmanned vehicles, more and more sensors and electronic units are used, with machine learning and AI control are the key projects of future development. Because machine learning can design and analyze some computer or embedded system can automatically "learn" the algorithm, with the number of training to automatically analyze the rules, and the use of laws to predict the unknown data is very suitable for use in the complex unmanned vehicle system.
Because of the complexity of the vehicle network, the bandwidth usage of the existing CAN network is close to the technical limit. As a result, Bosch introduced the CAN FD protocol in 2012. And CAN FD inherits the main characteristics of CAN. Therefore, it is very important to study the hybrid CAN and CAN FD networks.
However, how to effectively use bandwidth in CAN FD is still a problem. This paper presents a method for CAN FD machine learning K-means data grouping and hybrid CAN and CAN FD networks, this method is used as the data grouping of CAN FD, and the reference of CAN FD data is changed as the priority of data, so that the bandwidth of CAN FD network is effectively utilized.
This research is divided into two parts, the first part is to use machine learning K-means method to do data clustering simulation, the data according to the result of clustering, change CAN FD data in the arbitration phase. The second part realizes the hybrid CAN and CAN FD network, and uses the ECU sim2000 OBD-II simulator and the hand-held vehicle online diagnosis system as the test and verification of this system.
Finally, after the integration test of this research, it is proved that this design can not only be compatible with the current CAN vehicle network, but also can change the CAN FD message according to the grouping result after experimental K-means processing six different data amount of CAN FD message grouping. The priority order can effectively reduce the data loss rate of the CAN FD network. Among them, the rate of CAN FD arbitration phase is 1Mbps and the data phase is 2Mbps and 4Mbps respectively, the data loss rate is reduced by 2.86% and 2.58%, which provides better reliability for CAN FD network.

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 研究背景...1
1.2 動機與目的...1
1.3 國內外之相關研究情況...2
1.4 論文章節概述...3
第二章 系統原理...4
2.1 機器學習...4
2.1.1 K-means簡介...4
2.1.2 K-means演算法描述...4
2.1.3 K-means相關應用...5
2.1.4 K-means與其他機器學習的方法關係...6
2.2 CAN匯流排通訊協定...6
2.2.1 CAN簡介...6
2.2.2 CAN通訊協定之模型架構...8
2.2.3 CAN通訊協定之通訊格式...8
2.3 CAN FD匯流排通訊協定...10
2.3.1 CAN FD簡介...10
2.3.2 CAN FD基本概念...11
2.3.3 CAN FD通訊協定之通訊格式...12
2.3.4 CAN FD效能表現...13
2.3.5 CAN FD相關硬體支援...14
2.4 SPI通訊協定...14
2.4.1 SPI簡介...14
2.4.2 SPI原理...14
2.5 UART通訊協定...16
2.6 OBD-II特性與原理...17
2.6.1 OBD-II簡介...17
2.6.2 OBD-II通訊協定與標準規格...17
2.7 ECU sim2000 OBD-II Simulator簡介...18
2.8 VEDIS II簡介...20
2.9 PCAN-USB Pro FD分析儀簡介...21
第三章 系統設計...22
3.1 系統架構...22
3.2 CAN FD網路架構設計...23
3.3 CAN FD ECU設計...24
3.4 CAN FD/CAN閘道器設計...26
3.4.1 閘道器1-ECU sim2000 OBD-II Simulator閘道器設計...26
3.4.2 閘道器2-VEDIS II手持式車輛連線診斷系統閘道器設計...28
3.5 CAN數位儀表設計...29
3.6 K-means分群設計...32
3.6.1 CAN FD隨機資料產生器...33
3.6.2 K-means歐幾里得平方距離方法資料分群...38
3.6.3 K-means絕對誤差和方法資料分群...41
第四章 系統測試...46
4.1 CAN FD通訊驗證...47
4.2 CAN 通訊驗證...49
4.3 SPI 主從介面通訊驗證...50
4.4 CAN FD/CAN閘道器測試...51
4.4.1 閘道器1-ECU sim2000 OBD-II Simulator閘道器驗證...52
4.4.2 閘道器2-VEDIS II手持式車輛連線診斷系統閘道器驗證...54
4.5 CAN數位儀表測試...57
4.6 K-means分群驗證測試...59
4.6.1 K-means歐幾里得平方距離方法資料分群...63
4.6.2 K-means絕對誤差和方法資料分群...67
4.6.3 K-means歐幾里得平方距離和絕對誤差和方法結果分析...71
第五章 結論與未來展望...72
5.1 結論...72
5.2 未來展望...72
參考文獻....73
Abstract...75

[1]Machine learning-Wiki https://en.wikipedia.org/wiki/Machine_learning
[2]Meiqin Mao, Yangyang Wang, You Yue, 2017,"“Multi-time scale forecast for
schedulable capacity of EVs based on big data and machine learning", IEEE
Energy Conversion Congress and Exposition (ECCE), pp.1425-1431, Cincinnati,
OH, USA, 1-5 Oct
[3]Le Luong Vy, Li-Ping Tung, Bao-Shuh Paul Lin, 2017,"Big data and machine
learning driven handover management and forecasting", IEEE Conference on
Standards for Communications and Networking (CSCN), pp.214-219, Helsinki,
Finland, 18-20 Sept
[4]Fuchun Sun, Guang-Bin Huang, Q. M. Jonathan Wu, 2017,“Efficient and Rapid
Machine Learning Algorithms for Big Data and Dynamic Varying Systems” ,
IEEE Transactions on Systems, Man, and Cybernetics: Systems , Volume: 47,
pp.2625-2626, 1 Sept
[5]Cen Chen, Kenli Li, Aijia Ouyang,"GPU-Accelerated Parallel Hierarchical
Extreme Learning Machine on Flink for Big Data”" , IEEE Transactions on
Systems, Man, and Cybernetics: Systems, Volume: 47, pp.2740-2753, 24 April
[6]Jeannette Chin, Vic Callaghan, Ivan Lam, 2017,"Understanding and
personalising smart city services using machine learning, The Internet-of-
Things and Big Data" , International Symposium on Industrial Electronics
(ISIE), Edinburgh, UK, 19-21 June
[7]Min Chen, Yixue Hao, Kai Hwang, 2017, "Disease Prediction by Machine
Learning Over Big Data From Healthcare Communities" , IEEE Access , Volume:
5, pp.8869-8879, April
[8]Yung Hoh Sheu, Zuo Wen Wang, Yao Jhong Liou,2014, "The K-Means Clustering
Methods Applied in the Message Scheduling Methods of FlexRay Communication
Network Based on the Embedded FlexRay Node", 2014 Tenth International
Conference on Intelligent Information Hiding and Multimedia Signal
Processing, pp.179-182, Kitakyushu, Japan, 27-29 Aug
[9]Shan Ding, Ruifeng Huang, Ryo Kurachi, Gang Zeng,2016, "A Genetic Algorithm
for Minimizing Bandwidth Utilization by Packing CAN FD Frame", 2016 13th
International Conference on Embedded Software and Systems (ICESS), pp.
(s):119-124, Chengdu, China, 13-14 Aug
[10]Amit Kumar Sinha, Jae Wook Jeon, 2017, "CAN FD: Performance reality", 2017
3rd International Conference on Computational Intelligence & Communication
Technology (CICT), pp.1-6,Ghaziabad, India, 9-10 Feb
[11]Hyun Su An, 2017,"Analysis of CAN FD to CAN message routing method for CAN
FD and CAN gateway", 2017 17th International Conference on Control,
Automation and Systems (ICCAS), Jeju, South Korea, 18-21 Oct
[12]Prachi Joshi, S.S. Ravi, Soheil Samii, 2017, "Offset Assignment to Signals
for Improving Frame Packing in CAN FD", 2017 IEEE Real-Time Systems
Symposium (RTSS), Paris, France, 5-8 Dec
[13]Mehmet Ertu Afin, Klaus Werner Schmidt, Ece Guran Schmidt, 2017, "A
Configurable CAN FD controller: Architecture and implementation", 2017 25th
Signal Processing and Communications Applications Conference (SIU),
Antalya, Turkey, 15-18 May
[14]K-means http://mirlab.org/jang/books/dcpr/kMeans.asp?title=3-3%20K-
means%20%A4%C0%B8s%AAk
[15]K-means clustering https://en.wikipedia.org/wiki/K-means_clustering
[16]Coates, Adam; Ng, Andrew Y. Learning feature representations with k-means
[17]Honarkhah, M and Caers, J, 2010, "Stochastic Simulation of Patterns Using
Distance-Based Pattern Modeling", Mathematical Geosciences, 42: 487 - 517
[18]Press, WH; Teukolsky, SA; Vetterling, WT; Flannery, BP. Section 16.1.
Gaussian Mixture Models and k-Means Clustering. Numerical Recipes: The Art
of Scientific Computing 3rd. New York: Cambridge University Press. 2007
[19]Little, M.A.; Jones, N.S. Generalized Methods and Solvers for Piecewise
Constant Signals: Part I (PDF). Proceedings of the Royal Society A. 2011.
[20]H. Zha, C. Ding, M. Gu, X. He and H.D. Simon, 2001, "Spectral Relaxation
for k-means Clustering", Neural Information Processing Systems, Volume:14,
pp.(s):1057-1064 ,Vancouver, Canada, 3-8 Dec.
[21]Chris Ding and Xiaofeng He. k-means Clustering via Principal Component
Analysis (PDF). Proc. of Int'l Conf. Machine Learning (ICML 2004). July
2004: 225–232.
[22]Alon Vinnikov and Shai Shalev-Shwartz. k-means Recovers ICA Filters when
Independent Components are Sparse (PDF). Proc. of Int'l Conf. Machine
Learning (ICML 2014).
[23]許永和，2011，智慧車載資通訊實驗系統，初版，台灣優奎士有限公司，高雄市。
[24]Robert Bosch GmbH, Robert Bosch Platz 1, 70839 Gerlingen, Germany
[25]VeCo12_8_NewBusSystems_3_Lindenkreuz_Lecture.pdf
[26]許永和，2011，介面設計與實習 PSOC與感測器實務應用，全華圖書，新北市。
[27]林峻毅，2006，"車上診斷系統(OBD)簡介"，財團法人車輛研究測試中心知識庫。
[28]Keyvan Ansari, Charles Wang, Lei Wang and Yanming Feng, 2013,
"Vehicle-to-Vehicle Real-Time Relative Positioning Using 5.9GHz DSRC
Media", IEEE Vehicular Technology Conference, pp.(s):1-7, Las Vegas, NV,
USA, 2-5 Sept.
[29]Society of Automotive Engineers, 2001, "SAE J1962 - Diagnostic
Connector Equivalent to ISO/DIS 15031".
[30]Ricardo De Andrade, Kleber N. Hodel , João Francisco Justo, Armando M.
Laganá,Max Mauro Santos, Zonghua Gu , 2018, "Analytical and Experimental
Performance Evaluations of CAN-FD Bus" , IEEE Access , Volume:6, pp.
(s):21287-21295, 16 April
[31]LPC54618，Datasheet.
[32]JLX-12864，Datasheet.