字體大小: 字級放大   字級縮小   預設字形  

詳目顯示

以作者查詢圖書館館藏以作者&題名查詢臺灣博碩士以作者查詢全國書目
研究生中文姓名:朱寶瑩
研究生英文姓名:Chu, Pao-Ying
中文論文名稱:考量SKYPOOLING平台下航空公司裝載設備調度與規模之研究
英文論文名稱:Airline unit load device dispatching considering SKYPOOLING platform
指導教授姓名:湯慶輝
口試委員中文姓名:教授︰盧宗成
教授︰林振榮
學位類別:碩士
校院名稱:國立臺灣海洋大學
系所名稱:運輸科學系
學號:10768006
請選擇論文為:應用型
畢業年度:108
畢業學年度:107
學期:
語文別:中文
論文頁數:77
中文關鍵詞:裝載設備調度SKYPOOLING二項分布達成率配對成功率區間估計預計數量真實數量
英文關鍵字:Unit load devicedispatchingSKYPOOLINGbinomial distributionachievement ratepairing success rateinterval estimationestimated quantityreal quantity
相關次數:
  • 推薦推薦:0
  • 點閱點閱:35
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:4
  • 收藏收藏:0
航空公司裝載設備(Unit Load Device,簡稱ULD)包括貨盤與貨櫃,是航空公司每日營運不可或缺的重要設備。航空公司良好的ULD調度能有效提高ULD使用效率並降低ULD持有的規模。目前,SKYPOOLING平台是航空公司間ULD共享營運的一個新的免費平台,航空公司透過參與SKYPOOLING平台,可以相互借用ULD與請他航協助運送(即一般所稱協運),其目的即是希望透過共享的機制,能有效降低航空公司所需持有的ULD規模。另外,目前業者在SKYPOOLING運作上,每週會將所需借用與協運的ULD數量於平台上提出需求,但是在提出需求時並無考量SKYPOOLING借用與協運的成功配對率,此舉忽略預期借用與協運的數量於實際營運時的達成性,往往使得預期規劃的數量過於樂觀,造成原預期規劃結果與真實結果產生落差,降低SKYPOOLING的功效。有鑑於此,本研究考慮SKYPOOLING借用與協運之達成率,在業者希望之規劃達成率下,進行ULD的調度規劃。亦即本研究考慮SKYPOOLING借用與協運之規劃達成率、成功配對機率、借用與協運之預計與真實數量,以幫助業者規劃一滿足SKYPOOLING規劃達成率下的ULD調度規劃,以有效降發揮SKYPOOLING運作功效並降低業者ULD持有的規模。
本研究結合數學規劃中的時空網路與統計學中的二項分布與區間估計,建構一非線性混合整數模式。其中,時空網路用以定式各型ULD於各場站與時間之流動情形。另外,運用二項分布計算ULD借用與協運的達成率,以反應SKYPOOLING借用與協運之預計與真實數量。同時本研究亦利用區間估計技巧,以樣本成功配對機率估計母體成功機率之區間,將此區間加入模式之中,並將區間之下限與上限機率視為悲觀與樂觀情形,以進行分析。此外,本研究發展一反覆迭代啟發式求解演算法,利用分解式概念將模式分為不考慮達成率與考慮達成率之兩個子問題,之後再以基因改善機制求得改善解,再將求得之解反覆迭代回兩個子問題進行求解。最後,以國內航空公司資料為例進行分析,並根據研究的結果,提出結論與建議。
The Unit Load Device (ULD), including pallets and containers, is essential equipment for the airline's daily operations. A good ULD scheduling by airlines can effectively improve ULD usage efficiency and reduce the size of ULD holdings. Currently, the SKYPOOLING platform is a new free platform for ULD sharing operations between airlines. By participating in the SKYPOOLING platform, airlines can borrow ULD from each other and ask for assist in transportation, the purpose of which is to reduce the size of ULD that airlines need to hold by this sharing mechanism. However, the airline will put the demand on the platform every week, but it does not consider the successful matching rate of SKYPOOLING, which ignores the achievement of the number of the association's operations in actual operations. Thus, it makes the number of expected plans too optimistic, resulting in a gap between the original expected planning results and the real results, reducing the effectiveness of SKYPOOLING. In view of this, this study considers the achievement rate of SKYPOOLING borrowing and the cooperation and performs the scheduling planning of ULD under the planning achievement rate that the industry hopes. That is to say, this study considers the SKYPOOLING borrowing and the cooperation planning achievement rate, the successful matching probability, the borrowing, and the forecast and the actual quantity of the cooperation, to help the industry plan to meet the ULD scheduling plan under the SKYPOOLING planning achievement rate, effectively reduce the SKYPOOLING. It works and reduces the size of the industry's ULD holdings.
This study combines the binomial distribution and interval estimation in statistics and the time-space network in mathematical programming to construct a nonlinear mixed-integer model. Among them, the time-space network is used to determine the flow of various types of ULDs at each station and time. In addition, the binomial distribution used to calculate the achievement rate of ULD borrowing and cooperation, in order to reflect the expected and actual number of SKYPOOLING borrowing and cooperation. At the same time, this study also uses the interval estimation technique to estimate the probability of maternal success rate by the successful pairing probability of the sample, adding this interval to the model, and considers the lower limit of the interval and the upper limit probability as pessimistic and optimistic for analysis. In addition, this study develops a repeated iterative heuristic algorithm, which uses the concept of decomposition to divide the model into two sub-problems that do not consider the achievement rate and the achievement rate. We will apply the decomposition concept and the searching mechanism in a Genetic Algorithm to develop an iterated solution algorithm. We will perform a case study using the real operating data from a Taiwan airline. Finally, conclusions and suggestions will be given.
摘要 I
Abstract II
目錄 IV
表次 VII
第一章 緒論 1
1.1研究背景與動機 1
1.2 研究目的 2
1.3 研究範圍 3
1.4 研究流程 4
第二章 文獻回顧 5
2.1 航空公司ULD短期調度與規模 5
2.2 SKYPOOLING介紹與ULD運用SKYPOOLING之文獻 5
2.3 分解式演算法相關文獻 7
2.4 基因演算法(Genetic Algorithms, GA)相關文獻 9
2.5 本章小結 10
第三章 模式建構 12
3.1 問題描述 12
3.2 ULD時空網路設計 16
3.2.1 自有ULD時空網路 16
3.2.2 他航ULD時空網路 20
3.2.3 ULD載運與借用四種型態之時空網路流動 22
3.3 SKYPOOLING平台達成機率設計 26
3.3.1 達成率相關符號 26
3.2.2 達成率定式 27
3.4 模式定式 30
3.4.1 模式已知條件與假設 30
3.4.2 模式定式 30
3.5 問題規模 33
3.6 現況作法 34
第四章 啟發式求解演算法設計 35
4.1 演算法架構 35
4.2 子問題1與2 35
4.2.1 子問題1 35
4.2.2 子問題2 36
4.3 基因改善機制 37
4.3.1 編碼方式 37
4.3.2 初始解產生策略 38
4.3.3 適應值 38
4.3.4 選擇(Selection) 38
4.3.5 交配(Crossover) 38
4.3.6 突變(Mutation) 38
4.3.7 菁英政策 39
4.4 演算法整體流程 40
第五章 實證案例測試 42
5.1 資料輸入 42
5.1.1 航班資訊 42
5.1.2 各機型載運ULD相關資料 42
5.1.3 各型ULD裝拆打盤作業時間 43
5.1.4 各場站各類型ULD庫存需求量 44
5.2 模式輸入資料 44
5.3 電腦演算環境及設定 45
5.4 測試結果與分析 45
5.5 ULD SKYPOOLING配對分析 54
5.6 情境分析 61
5.6.1 未加入SKYPOOLING平台結果 61
5.6.2 現況作法比較 63
5.7 敏感度分析 69
第六章 結論與建議 73
6.1 結論 73
6.2 建議 74
參考文獻 75
1.SKYPOOLING平台網站
-https://skypooling.net/
2.王奕文,「隨機需求下運輸趟次規劃最佳化之研究」,碩士論文,國立臺灣海洋大學運輸科學學系,2018。
3.林鄉鎮、魏健宏,「應用類神經網路與遺傳演算法構建小汽車跟車模式之研究」,運輸計畫季刊,第二十八卷,第三期,頁353-378,1999
4.林孟嫻,「航空公司最適裝載設備調度與規模之研究」,碩士論文,國立交通大學運輸與物流管理學系,2017。
5.洪穎怡,「應用基因演算法規劃具間歇性負載工廠之變壓器容量」,碩士論文,中原大學電機工程學系,2002。
6.韋祿甄,「變動抽樣間隔EWMA 管制圖之經濟性設計」,碩士論文,國立雲林科技大學工業工程與管理研究所,2004。
7.陳建榮,「含凹行節線成本最小成本網路流動問題之全域搜尋演算法研究」,碩士論文,國立中央大學土木工程研究所,2002。
8.陳惠筑,「公路汽車客運多場站人員與車輛排班問題」,碩士論文,中華大學運輸科技與物流管理研究所,2006。
9.盧華安、陳倩怡、卓建宏、陳明宏,「國際航空貨運盤櫃設備最適規模及調度限制之研究」,運輸學刊,第二十一卷,第四期,頁385-412,2009。
10.謝國倫,「基因演算法應用於捷運轉乘公車區位路徑問題之研究」,碩士論文,淡江大學運輸管理研究所,1998。
11.藍武王、邱裕鈞,「線性軸輻路網接駁/轉運區位、路線與排班之規劃─遺傳演算法之應用」,第二十九卷,第三期,頁465-493,2000。
12.顏禎毅,「變動需求下航空公司裝載設備調度與規模之研究」,碩士論文,國立臺灣海洋大學運輸科學學系,2016。
13.Albayrak, M.,&Allahverdi, N. (2011), “Development a new mutation operator to solve the traveling salesman problem by aid of genetic algorithms,” Expert Systems with Applications, 38,3, pp.1313-1320.
14.Ali, H.,&Oh, S.C. (1996), “Formulation and solution of a multi-commodity, multi-modal network flow model for disasterrelief operations,” Transportation Research A, 30, 3, pp. 231-250.
15.Anne, M.,Cordeau, J. F.,&Fran.cois, S. (2005), “A computational study of Benders decomposition for the integrated aircraft routing and crew scheduling problem,” Computers&Operations Research, 32, 6, pp. 1451-1476.
16.Benet, C. H.,Kassler, A.,&Zola, E. (2016), “Predicting expected TCP throughput using genetic algorithm, ” Computer Networks, 108, pp.307-322.
17.Cheng, C. P.,Liu, C. W.,&Liu, C. C. (2000), “Unit commitment by lagrange relaxation and genetic algorithms,” IEEE Transactions on Power Systems,15, 2, pp.707-714.
18.Cramer, S.,Kampouridis, M., & Freitas, A. A. (2018), “Decomposition genetic programming: An extensive evaluation on rainfall prediction in the context of weather derivatives, ” Applied Soft Computing, 70, pp.208-224.
19.Doi, T., Nishi, T., & Voß, S. (2018), “Two-level decomposition-based matheuristic for airline crew rostering problems with fair working time, ” European Journal of Operational Research, 267,2, pp.428-438.
20.Goldberg, D. E., Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, Reading MA, 1989.
21.Joines, J. A., & Houck, C. R. , “On the Use of Non-stationary Penalty Functions to Solve Nonlinear Constrained Optimization Problems with GA’s,” IEEE World Congress on Computational Intelligence, 1994.
22.Lu, H. A., & Chen, C. Y. (2011), “A time–space network model for unit load device stock planning in international airline services, ”Journal of Air Transport Management,17,2, pp.94-100.
23.Lu, H. A., & Chen, C. Y. (2012), “Safety stock estimation of unit load devices for international airline operations,” Journal of Marine Science and Technology, 20,4, pp.431-440.
24.Mathias, K. E., & Whitley, L. D., “Initial performance comparisons for the delta coding algorithm,” The First IEEE Conference on Evolutionary Computation,1994.
25.Miranda, P. L., Cordeau, J.-F., Ferreira, D., Jans, R., & Morabito, R. (2018), “A Decomposition Heuristic for a Rich Production Routing Problem, ” Computers & Operations Research,98, pp.211-230.
26.Perl, J., & Daskin, M.S.(1985), “A warehouse location problem,” Transportation Research Part B, 19, 5, pp. 381-396.
27.Ramezani, F., & Lotfi, S., “ IAMGA: intimate-based assortative mating genetic algorithm,”International Conference on Swarm, Evolutionary, and Memetic Computing,2011.
28.Razali, N. M., & Geraghty, J., “Genetic algorithm performance with different selection strategies in solving TSP, ”The world congress on engineering conference,2011.
29.Reeves, C. (1997), “Genetic algorithms for the operations researcher,” INFORMS Journal on Computing, 9, 3, pp. 231-250.
30.Rudolph,G.(1994),“Convergence properties of canonical genetic algorithms,” IEEE Trans. Neural Networks,5, pp. 96-101.
31.Seiichi, K., Maggie, K. & Wayne, W. D. (1995), “Genetic simulated annealing and application to non-slicing floor plan design,” Baskin Center for Computer Engineering & Information Sciences University of California, Santa Cruz.
32.Simpson, R.W. , “A review of scheduling and routing model for airline scheduling,” IX AGIFORS Symposium,1969.
33.Srinivas, M. & Patnaik, L. M. (1994), “Adaptive probabilities of crossover and mutation in genetic algorithms,” IEEE Trans Syst., Man, and Cybern, 24 , pp.656-667.
34.Tang, C.H. (2011), “A scenario decomposition-genetic algorithm method for solving stochastic air cargo container loading problems,” Transportation Research Part E, 47, 4, pp. 520-531.
35.Tari, F. G., & Hashemi, Z. (2016), “A priority based genetic algorithm for nonlinear transportation costs problems, ” Computers & Industrial Engineering, 96, pp. 86-95.
36.Thierens, D., & Goldberg, D, “Elitist recombination: an integrated selection recombination GA,” The First IEEE Conference on Evolutionary Computation, 1994.
37.William, L.C., &Tito, H.D.M. (2007), “Some decomposition methods for revenue management,” Transportation Science, 41, 3, pp.332-353.
38.Wu, T.H., Chinyao, L., Bai, J.W. (2002), “Heuristic solutions to multi-depot location-routing problems,” Computers & Operations Research, 29, 10, pp. 1393-1415.

(此全文20240722後開放外部瀏覽)
電子全文
全文檔開放日期:2024/07/22
 
 
 
 
第一頁 上一頁 下一頁 最後一頁 top
* *