跳到主要內容

臺灣博碩士論文加值系統

(100.28.0.143) 您好!臺灣時間:2024/07/13 17:54
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:王瀞瑩
研究生(外文):Wang, Ching-Ying
論文名稱:結合系統動態學與長短期記憶神經網路預測銅金屬需求及價格
論文名稱(外文):Forecasting Copper Demand and Price by Combining System Dynamics and Long Short-Term Memory Models
指導教授:黃韻勳黃韻勳引用關係
指導教授(外文):Huang, Yun-Hsun
口試委員:吳榮華顏榮祥黃韻勳
口試委員(外文):Wu, Jung-HuaYen, Jung- HsiangHuang, Yun-Hsun
口試日期:2023-07-17
學位類別:碩士
校院名稱:國立成功大學
系所名稱:資源工程學系
學門:工程學門
學類:材料工程學類
論文種類:學術論文
論文出版年:2023
畢業學年度:111
語文別:中文
論文頁數:65
中文關鍵詞:銅金屬需求量預測銅金屬價格預測系統動態學長短期記憶神經網路
外文關鍵詞:Copper demand forecastingCopper price forecastingSystem dynamicsLong short-term memory neural network
相關次數:
  • 被引用被引用:0
  • 點閱點閱:58
  • 評分評分:
  • 下載下載:18
  • 收藏至我的研究室書目清單書目收藏:0
隨著近年來全球對淨零排放的追求,電動車的需求增加及再生能源產業興起,銅金屬需求量和價格預測遂成為重要議題。然而,多數研究僅使用單一方法預測銅金屬價格,難以全面考慮各因素對銅金屬市場之影響。本研究結合系統動態學及長短期記憶神經網路以預測銅金屬需求量和價格。首先透過系統動態學考量影響各子系統間的相互影響關係建立銅金屬需求量模型,再結合銅金屬需求量與銅價歷史數據以長短期記憶神經網路模型進行價格預測。
研究結果顯示,受能源政策、電動車發展、全球再生能源發展、建築部門等各產業銅需求量帶動下,2020年到2050年間全球的銅金屬需求量仍將持續上升。同時,汽車產業對於銅金屬的需求量比例持續上升,而其他產業的需求量占比則逐漸下降;此變化情況反映了全球在淨零轉型的過程下汽車產業電動化的趨勢以及銅金屬在此轉型過程中扮演的關鍵角色。此外,本研究結合系統動態學與長短期記憶神經網路模型後的均方誤差為0.1897、平均絕對百分比誤差為2.74%,且預測的價格趨勢與實際值相當一致,顯示不論從誤差指標或由價格趨勢的掌握程度,結合系統動態學與長短期記憶神經網路模型皆顯著優於傳統的長短期記憶神經網路模型。
本研究為國內首次在長短期記憶神經網路模型中結合系統動態學以預測銅金屬需求及價格,不僅可提高預測能力,更可提高模型的可視覺化與可解釋力,且能根據預測結果,對投資者、銅生產商、銅關鍵消費產業、政府與監管機構等利害關係人提供決策支援。
The global pursuit of net-zero emissions and emergence of electric vehicles are driving demand for copper. Most previous research on forecasting copper markets has relied on simple methods that cannot account for the wide range of factors affecting supply and demand. In the current study, we used system dynamics to model the interrelationships among the various subsystems driving demand, and then combined those results with historical copper price data to predict prices using a long short-term memory (LSTM) neural network.
Our findings revealed that the global demand for copper will continue increasing until at least 2050, under the effects of energy policy, the expansion of electric vehicles, ongoing developments in renewable energy, and growth in the construction sector. Note that the share of copper demand from the automotive industry will steadily increase, while the share of demand from other industries will decline. This shift reflects the trend toward electric vehicles and the transition to net-zero emissions, which is driving demand for electricity and corresponding infrastructure. The price evolution predicted in the current study is consistent with the actual values, and our combined use of system dynamics with an LSTM model proved highly accurate in terms of mean square error (0.1897) and mean absolute percentage error (2.74%).
The integration of system dynamics within an LSTM model was shown to enhance the predictive capabilities of the model, while facilitating the visualization and interpretation of the results. Accurate prediction results provide crucial decision support for investors, copper producers, key consumer industries, governments, and regulators.
中文摘要 I
Abstract II
誌謝 VI
目錄 VII
表目錄 VIII
圖目錄 IX
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研究內容與架構 4
第二章 文獻回顧 7
2.1銅金屬市場之研究 7
2.2系統動態學應用於銅金屬需求量之研究 9
2.3長短期記憶神經網路應用於價格預測之研究 11
2.4本章小結 13
第三章 研究方法 14
3.1系統動態學 14
3.2長短期記憶神經網路 17
3.3評估指標 23
3.4本章小結 24
第四章 模型建構 25
4.1系統動態模型建構 25
4.2資料預處理 36
4.3長短期記憶神經網路模型建構 36
第五章 模型結果與討論 41
5.1系統動態學模型測試 41
5.2系統動態學模型模擬銅金屬需求量之結果 42
5.3銅金屬期貨價格預測結果 48
5.4情境分析 52
第六章 結論與建議 57
6.1結論 57
6.2建議 58
6.3研究貢獻 59
參考文獻 60
中文部分:
1.中華系統動力學學會,擷取自https://systemdynamics.tw/www/2020-10-31-10-38-12。
2.交通環境資源處(2019),「廢棄物資源化–邁向循環經濟社會」,擷取自https://smmdb.epa.gov.tw/circulation/。
3.吳少鈞(2019),「以系統動力學探討土地利用變遷與交通運具選擇對於二氧化碳排放之影響-以高雄市為例」國立中山大學海洋環境及工程學系碩士論文。
4.李旭(2008),「社會系統動力學-政策研究的原理、方法和應用」,復旦大學出版社。
5.屠益民、張良政(2010)「系統動力學:理論與應用」,智勝書局出版。
6.陶在樸(2016),「系統動力學入門」,五南圖書出版社。
7.黃文章(2023),「能源轉型將帶動未來幾年銅金屬需求量年均增長2.7%」MoneyDJ理財網。
8.楊子震 (2010),「以系統動力學探討創新醫療模式之績效-以台大醫院病患自控止痛服務小組為例」,國立台灣大學管理學院商學研究所碩士論文。
9.楊朝仲、張良正、葉欣誠、陳昶憲、葉昭憲(2009),「系統動力學思維與應用」,五南圖書出版社。
10.葉貞君、楊宗穎、沈柏丞、郭傳薪、黃柏元、林彥均、張嘉諳、張凱翔、陳斌魁 (2016),「推動再生能源面臨的議題」,臺灣能源期刊,3(4),385-415。
11.韓釗(2008),「系統動力學:探討動態複雜之鑰」,滄海書局出版。 
英文部分:
1.Agusdinata, D. B., Eakin, H., & Liu, W. (2022). Critical minerals for electric vehicles: A telecoupling review. Environmental Research Letters, 17(1), 013005.
2.Auping, W., Pruyt, E., & Kwakkel, J. (2012). Analysing the uncertain future of copper with three exploratory system dynamics models. In Proceedings of the 30th International Conference of the System Dynamics Society.
3.Barlas, Y., & Carpenter, S. D. M. (1990). Philosophical roots of model validation: two paradigms. System Dynamics Review, 6, 148-166.
4.Bullard, N. (2022). Surging Copper Demand Will Complicate the Clean Energy Boom. Bloomberg. Retrieved from https://www.bloomberg.com/news/articles/2022-09-01/copper-demand-to-rise-50-by-2040-as-clean-energy-takes-hold.
5.Chen, J., Li, T., Cheng, J., & Fang, C. (2022). Copper Price Prediction Using LSTM Recurrent Neural Network and Simulation Annealing Algorithm, Available at SSRN 4036260.
6.Deetman, S., de Boer, H. S., Van Engelenburg, M., van der Voet, E., & van Vuuren, D. P. (2021). Projected material requirements for the global electricity infrastructure – generation, transmission and storage. Resources, Conservation & Recycling, 164, 105200.
7.Deetman, S., Marinova, S., van der Voet, E., van Vuuren, D. P., Edelenbosch, O., & Heijungs, R. (2020). Modelling global material stocks and flows for residential and service sector buildings towards 2050. Journal of Cleaner Production, 245, 118658.
8.Deetman, S., Pauliuk, S., van Vuuren, D. P., van der Voet, E., & Tukker, A. (2018). Scenarios for demand growth of metals in electricity generation technologies, cars, and electronic appliances. Environmental Science & Technology, 52(8), 4950–4959.
9.Forrester, J. W. (1968). Industrial dynamics- after the first decade. Management Science, 14(7), 398-415.
10.He, Z., Zhou, J., Dai, H. -N., & Wang, H. (2019). Gold price forecast based on LSTM-CNN model. In 2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech), pp.1046-1053.
11.Hu, Y., Ni, J., & Wen, L. (2020). A hybrid deep learning approach by integrating LSTM-ANN networks with GARCH model for copper price volatility prediction. Physica A: Statistical Mechanics and its Applications, 557, 124907.
12.International Energy Agency (IEA) (2021). The Role of Critical Minerals in Clean Energy Transitions. IEA, Paris. Retrieved from https://www.iea.org/reports/the-role-of-critical-minerals-in-clean-energy-transitions
13.International Copper Association (ICA) (2023). The Power of Zero. Retrieved from https://copperalliance.org/
14.Investing.com. (2023). Copper Contracts. Retrieved from https://hk.investing.com
15.Jia, M., Huang, J., Pang, L., & Zhao, Q. (2019). Analysis and research on stock price of LSTM and bidirectional LSTM neural network. In 3rd International Conference on Computer Engineering, Information Science & Application Technology (ICCIA 2019), pp. 467-473.
16.Klose, S., & Pauliuk, S. (2023). Sector-level estimates for global future copper demand and the potential for resource efficiency. Resources, Conservation & Recycling, 193, 106941.
17.Lin, O. Z., & Miyauchi, H. (2017). Optimal replacement time of electrical components based on constant-Interval replacement model: equipment inspection method and Weibull analysis. Energy and Power Engineering, 9, 475-485. doi:10.4236/epe.2017.94B053
18.Liu, K., Cheng, J., & Yi, J. (2022). Copper price forecasted by hybrid neural network with Bayesian Optimization and wavelet transform. Resources Policy, 75, 102520.
19.Luo, H., Wang, D., Cheng, J., & Wu, Q. (2022). Multi-step-ahead copper price forecasting using a two-phase architecture based on an improved LSTM with novel input strategy and error correction. Resources Policy, 79, 102962.
20.Månberger, A., & Stenqvist, B. (2018). Global metal flows in the renewable energy transition: exploring the effects of substitutes, technological mix and development. Energy Policy, 119, 226-241.
21.McKinsey Energy. (2021). MineSpans Copper Demand Model Q3. Retrieved from https://www.mckinsey.com/industries/metals-and-mining/how-we-help-clients/minespans/overview.
22.Meadows, D. H., Meadows, D. L., Randers, J., & Behrens, W. W. (1972). The Limits to Growth. Universe Books.
23.Mudd, G. M., & Jowitt, S. M. (2018). Growing global copper resources, reserves and production: discovery is not the only control on supply. Economic Geology, 113(6), 1235-1267.
24.National Minerals Information Center (2023). Copper Statistics and Information. Retrieved from https://www.usgs.gov/centers/national-minerals-information-center/copper-statistics-and-information
25.Olah, C. (2015). Understanding LSTM Networks. Retrieved from http://colah.github.io/posts/2015-08-Understanding-LSTMs/
26.Ozdemir, A. C., Buluş, K., & Zor, K. (2022). Medium- to long-term nickel price forecasting using LSTM and GRU networks. Resources Policy, 78, 102906.
27.Peng, Z. Y., & Guo, P. C. (2022). A data organization method for LSTM and transformer when predicting Chinese banking stock prices. Discrete Dynamics in Nature and Society, 2022, 1-8.
28.Peretto, P. F. (1998). Technological Change and Population Growth. Journal of Economic Growth, 3, 283-311.
29.Singhal (2020). Introduction to LSTM Units in RNN. Retrieved from https://www.pluralsight.com/guides/introduction-to-lstm-units-in-rnn
30.S&P Global (2022). The Future of Copper: Will the looming supply gap short-circuit the energy transition? Retrieved from https://www.spglobal.com/en/
31.S&P Global (2022). World copper deficit could hit record; demand seen doubling by 2035: S&P Global. Retrieved from https://www.spglobal.com/commodityinsights/zh
32.Schipper, B. W., Lin, H. C., Meloni, M. A., Wansleeben, K., Heijungs, R., & van der Voet, E. (2018). Estimating global copper demand until 2100 with regression and stock dynamics. Resources, Conservation and Recycling, 132, 28-36.
33.Sterman, J. D. (1989). Modeling Managerial Behavior: Misperceptions of Feedback in a Dynamic Decision Making Experiment. Management Science, 35, 321-339.
34.Sterman, J. D. (2000). Business Dynamics: Systems Thinking and Modeling for a Complex World. Irwin McGraw-Hill.
35.Tilton, J. E. (1996). Exhaustible resources and sustainable development: Two different paradigms. Resources Policy, 22(1-2), 91-97.
36.Yang, J., Li, X., & Liu, Q. (2017). China’s copper demand forecasting based on system dynamics model: 2016-2030. Journal of Residuals Science & Technology, 14(3), 651-660.
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