進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-1608201808161900
論文名稱(中文) 應用多目標演化式演算法於危險物品運輸路徑規劃
論文名稱(英文) A Multi-objective Evolutionary Algorithm for Hazmat Transportation Route Planning
校院名稱 成功大學
系所名稱(中) 交通管理科學系
系所名稱(英) Department of Transportation & Communication Management Science
學年度 106
學期 2
出版年 107
研究生(中文) 許佳汎
研究生(英文) Chia-Fan Hsu
電子信箱 fran830325fn@gmail.com
學號 R56054078
學位類別 碩士
語文別 英文
論文頁數 83頁
口試委員 指導教授-胡大瀛
口試委員-胡守任
口試委員-董啟崇
中文關鍵字 危險物品運輸  多目標  基因演算法  緊急恢復力  路徑規劃 
英文關鍵字 Hazmat transportation  multi-objective  routing design  genetic algorithm  emergency response capability 
學科別分類
中文摘要 危險物品運輸途中意外的發生往往直接影響到事發地點周遭的居民安全、環境、以及造成交通壅塞、阻斷等。路徑規劃則為一牽扯多項因素之多目標問題,以危險物品運輸為例,運輸成本、運輸途中發生意外所帶來之風險,皆為過去研究中基本考量目標,而本研究加入之緊急恢復力,為研究危險物品運輸中較少考慮之目標,是為評估意外發生時之救援程度以及路網恢復能力。
2014年高雄化學氣爆案的發生,不僅損壞重要道路、也帶來嚴重傷亡,氣爆案發生的原因為運送危險物品之管線破損,導致運送液態丙烯外洩,引起事故。此次意外發生使得高雄市居民憂慮危險物品管線運輸之安全性,因此高雄市政府宣布不再修復以及使用這些管線,且以化學槽車取代管線運輸載運危險物品,但同時危險物品所帶來的風險也移轉至緊鄰建築物的道路上。於此,本研究認為,危險物品運輸路徑規劃問題顯而易見地尤其重要。儘管國外對於危險物品路徑規劃之研究已不少且趨於完整,但臺灣地區尚未有完善的管理部門以及研究,所以本研究之主要目的為,對於臺灣之危險物品運輸,尋找適合之研究方法並建立對應的模型進行危險物品運輸的路徑規劃。
本研究選擇使用基因演算法處理多目標危險物品運輸路徑規劃問題並以產生之結果與以多目標妥協權重法之結果比較,同時針對高雄氣爆案周遭路網做實證研究,將兩種方法產生之結果繪於真實路網中進行比較分析。經由更精確的資料蒐集與分析,最終產生之結果可供政府參採。
英文摘要 Hazmat transportation can seriously impact human life, environment and cause congestion or disruption in transport system if accidents occur through transportation process. Route planning of hazmat transportation is definitely a multi-objective problem involving multiple factors such as cost, risk for the most researches in the past. Moreover, the “Emergency response capability” is added to consider in this research which is an objective aiming to evaluate the rescue capability and resilience of network when an accident is happened.
As a result of the 2014 Kaohsiung gas explosion event, the policy claimed to use chemical tank car instead of pipeline transporting hazmat, simultaneously, making the risk of hazard material shift to the road. Therefore, hazmat transportation route design and management is surely significant. Although there are many related researches existed, Taiwan still does not have a complete and integrated department yet. The various methods of dealing hazmat transporting problem were proposed, so the main goal of this research is constructing a suitable approach to build an appropriate model to manage the transport route for hazmat shipping in Taiwan.
By choosing the genetic evolution algorithm to deal with the multi-objective hazmat transportation problem, the research also comparing the result with compromise weight method. Empirical study of Kaohsiung explosion network is implemented to illustrate the solution and analysis of the design. Through the right data input, the results can provide some suggestions for hazmat transporting route design in urban transportation system.
論文目次 ABSTRACT I
摘要 II
誌謝 III
TABLE OF CONTENTS IV
LIST OF TABLES VII
LIST OF FIGURES IX
CHAPTER 1 INTRODUCTION 1
1.1 Research Background and Motivation 1
1.2 Research Objectives 2
1.3 Research Flow Chart 3
CHAPTER 2 LITERATURE REVIEW 6
2.1 Hazmat Transportation in Taiwan 6
2.2 Hazmat Transportation 10
2.3 Recent Researches of Hazmat Transportation 12
2.3.1 Method application of Hazmat Transportation 12
2.3.2 Single and Multiple Origin-Destination of Hazmat Transportation 13
2.4 Application of Multiple Objective Approach in Hazmat Transportation 13
2.5 Risk on Hazmat Transportation 15
2.6 Emergency Response Capability 17
2.7 Multi-objective Optimization Approach 20
2.7.1 Model of Multi-Objective Optimization 20
2.7.2 Multi-objective Genetic Algorithm 24
2.8 Summary 29
CHAPTER 3 RESEARCH METHODOLOGY 31
3.1 Problem Statement and Research Assumption 31
3.2 Research Framework 32
3.3 Model Formulation 35
3.3.1 Definition of Criteria 35
3.3.2 Formulation 36
3.4 Solution Algorithm Framework 40
3.5 Data Description 47
3.5.1 Basic Data of Experimental Network 47
3.5.2 Conditional Release Probability 48
3.5.3 Accident Rate 49
3.5.4 Hazmat Impact Radius 50
3.5.5 Fire Service Resource 52
CHAPTER 4 EMPIRICAL EXPERIMENT 53
4.1 Experiment Design 53
4.1.1 Basic data of Experimental Network 53
4.1.2 Program Architecture 54
4.1.3 Multiple Origin Destination pairs 58
4.2 Experiment Results 60
4.2.1 Basic Experiment and Parameter Calibration 60
4.2.2 Sensitivity Analysis of Crossover Rate 66
4.2.3 Sensitivity Analysis of Mutation Rate 68
4.2.4 Compare NSGA Ⅱ with Compromise Weight Method 70
4.2.5 Characteristic of NSGA Ⅱ 74
4.3 Summary 75
CHAPTER 5 CONCLUSIONS AND SUGGESTIONS 76
5.1 Conclusions 76
5.2 Suggestions 77
REFERENCE 78
參考文獻 1. Auger, A., Bader, J., Brockhoff, D., & Zitzler, E. (2009). Theory of the hypervolume indicator: optimal μ-distributions and the choice of the reference point. Paper presented at the Proceedings of the tenth ACM SIGEVO workshop on Foundations of genetic algorithms.
2. Berman, O., Verter, V., & Kara, B. Y. (2007). Designing emergency response networks for hazardous materials transportation. Computers & operations research, 34(5), 1374-1388.
3. Cappanera, P., & Nonato, M. (2014). The Gateway Location Problem: a cost oriented analysis of a new risk mitigation strategy in hazmat transportation. Procedia-Social and Behavioral Sciences, 111, 918-926.
4. Chakrabarti, U. K., & Parikh, J. K. (2013). A societal risk study for transportation of class-3 hazmats–A case of Indian state highways. Process Safety and Environmental Protection, 91(4), 275-284.
5. Chen, Y.-W., Wang, C.-H., & Lin, S.-J. (2008). A multi-objective geographic information system for route selection of nuclear waste transport. Omega, 36(3), 363-372.
6. Deb, K. (2001). Multi-objective optimization using evolutionary algorithms (Vol. 16): John Wiley & Sons.
7. Deb, K., Agrawal, S., Pratap, A., & Meyarivan, T. (2000). A fast elitist non-dominated sorting genetic algorithm for multi-objective optimization: NSGA-II. Paper presented at the International Conference on Parallel Problem Solving From Nature.
8. Erkut, E., & Verter, V. (1998). Modeling of transport risk for hazardous materials. Operations Research, 46(5), 625-642.
9. Faghih-Roohi, S., Ong, Y.-S., Asian, S., & Zhang, A. N. (2016). Dynamic conditional value-at-risk model for routing and scheduling of hazardous material transportation networks. Annals of Operations Research, 247(2), 715-734.
10. Fonseca, C. M., & Fleming, P. J. (1993). Genetic Algorithms for Multiobjective Optimization: FormulationDiscussion and Generalization. Paper presented at the Icga.
11. Fritelli, J., Parfomak, P. W., Ramseur, J. L., Andrews, A., Pirog, R., & Ratner, M. (2014). US rail transportation of crude oil: background and issues for Congress (R43390). Retrieved from Congressional Research Service:
12. Giannikos, I. (1998). A multiobjective programming model for locating treatment sites and routing hazardous wastes. European Journal of Operational Research, 104(2), 333-342.
13. Hancock, K., Abkowitz, M., & Lepofsky, M. (1993). Assessing hazardous materials emergency response capability: methodological development and application. Transportation Research Record(1383).
14. Harwood, D. W., Viner, J. G., & Russell, E. R. (1993). Procedure for developing truck accident and release rates for hazmat routing. Journal of Transportation engineering, 119(2), 189-199.
15. Hazardous Material Transportation Act of 1975, § 49 U.S.C. §§ 5101-5127 (1975).
16. Holland, J. H. (1992). Adaptation in natural and artificial systems. 1975. Ann Arbor, MI: University of Michigan Press and.
17. Karim, L., Boulmakoul, A., Mabrouk, A., & Lbath, A. (2017). Deploying Real Time Big Data Analytics in Cloud Ecosystem for Hazmat Stochastic Risk Trajectories. Procedia Computer Science, 109, 180-187.
18. Konak, A., Coit, D. W., & Smith, A. E. (2006). Multi-objective optimization using genetic algorithms: A tutorial. Reliability Engineering & System Safety, 91(9), 992-1007.
19. Landucci, G., Antonioni, G., Tugnoli, A., Bonvicini, S., Molag, M., & Cozzani, V. (2017). HazMat transportation risk assessment: A revisitation in the perspective of the Viareggio LPG accident. Journal of Loss Prevention in the Process Industries, 49, 36-46.
20. Li, R., Leung, Y., Huang, B., & Lin, H. (2013). A genetic algorithm for multiobjective dangerous goods route planning. International Journal of Geographical Information Science, 27(6), 1073-1089.
21. LIAO, T.-Y., HU, T.-Y., CHANG, Y.-H., & HSU, C.-F. (2017). A Multi-objective Compromise Weight Model for Hazmat Transportation Problems with the Consideration of Response Capability. Journal of the Eastern Asia Society for Transportation Studies, 12, 2035-2053.
22. Mohammadi, M., Jula, P., & Tavakkoli-Moghaddam, R. (2017). Design of a reliable multi-modal multi-commodity model for hazardous materials transportation under uncertainty. European Journal of Operational Research, 257(3), 792-809.
23. Murata, T., & Ishibuchi, H. (1995). MOGA: Multi-objective genetic algorithms. Paper presented at the Evolutionary Computation, 1995., IEEE International Conference on.
24. Samanlioglu, F. (2013). A multi-objective mathematical model for the industrial hazardous waste location-routing problem. European Journal of Operational Research, 226(2), 332-340.
25. Schaffer, J. D. (1985). Some experiments in machine learning using vector evaluated genetic algorithms. Retrieved from
26. Shang, H., Wang, X., & Liu, X. (2007). Application of Fuzzy Assessment Method to Emergency Response Capability in Hazardous Materials Transportation. Paper presented at the Innovative Computing, Information and Control, 2007. ICICIC'07. Second International Conference on.
27. Torretta, V., Rada, E. C., Schiavon, M., & Viotti, P. (2017). Decision support systems for assessing risks involved in transporting hazardous materials: a review. Safety Science, 92, 1-9.
28. Westenhaus, B. (2013). Trucks, Trains, or Pipelines–The Best Way to Transport Petroleum. Retrieved from NEW ENERGY AND FUEL website: http://newenergyandfuel.com/http:/newenergyandfuel/com/2013/08/13/trucks-trains-or-pipelines/
29. Wijeratne, A. B., Turnquist, M. A., & Mirchandani, P. B. (1993). Multiobjective routing of hazardous materials in stochastic networks. European Journal of Operational Research, 65(1), 33-43.
30. Zografos, K. G., & Davis, C. F. (1989). Multi-objective programming approach for routing hazardous materials. Journal of Transportation engineering, 115(6), 661-673.
31. Chinatimes.com 《槽車惹禍 環團:全面評估石化業風險》
http://www.chinatimes.com/newspapers/20140813000379-260102
32. Chinatimes.com《硫酸槽車翻覆國道 拖板車撞上救援消防車造成3人輕重傷》http://www.chinatimes.com/realtimenews/20160407002328-260402
33. ETtoday東森新聞雲《貢寮化學槽車翻覆鹽酸外洩 駕駛慘被護欄腰斬拋車外》http://www.ettoday.net/news/20160710/732488.htm
34. Liberty Times Net《化學槽車五股翻覆 傳漏4千公升氯化銅》http://news.ltn.com.tw/news/society/breakingnews/2021652
35. Liberty Times Net《驚險!化學槽車翻覆 濱海公路一度大塞車》
http://news.ltn.com.tw/news/society/breakingnews/2066114
36. Liberty Times Net《載鹽酸槽車翻覆!國1北上嘉義水上路段管制警戒》
http://news.ltn.com.tw/news/society/breakingnews/2073239
37. Liberty Times Net《化學槽車國道翻覆 二第三丁基酚幸未外洩》http://news.ltn.com.tw/news/society/paper/980288
38. 道路交通安全規則(民100年4月14日)第八十四條
39. 陳立國、陳乃瑜、賴興俊(民103年8月4日)。獨家/「知道管線很多」24年前公文曝光!吳敦義批准埋的。三立新聞網。取自https://www.setn.com/News.aspx?NewsID=33800
40. 高雄市政府交通局《高雄市運送危險物品罐槽車限定行駛路線》
http://www.tbkc.gov.tw/AService0108_08.aspx
41. 中華民國工業科技安全衛生協會《危險物品運送人員-其他貨車初訓》
http://www.istsha.org.tw/Knowledge_show-0a10102.html
42. 中華民國交通部公路總局《危險物品車輛限定、禁止或建議行駛路段》
https://www.thb.gov.tw/page?node=a5fcbd75-0ee2-4913-95cb-91e076f14838
43. 中華民國交通部國道高速公路局《特殊車輛管制資訊》
http://www.freeway.gov.tw/Publish.aspx?cnid=520&p=133
44. 社團法人中華壓力容器協會《道路危險物品運送人員訓練》
http://www.pva.org.tw/office/index.php/2014-11-19-06-35-14
45. 維基百科《2014高雄氣爆事故》https://zh.wikipedia.org/wiki/2014%E5%B9%B4%E9%AB%98%E9%9B%84%E6%B0%A3%E7%88%86%E4%BA%8B%E6%95%85
46. 聯合新聞網《液氮化學槽車突爆胎起火 消防射水搶救降溫》https://udn.com/news/story/2/2371214
47. 馬振基. 2014.「高雄氣爆百日後」的再思---對未來「石化管線設置、維護」的建言.科技報導396期
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2023-08-16起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2023-08-16起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw