| 研究生: |
林怡君 Lin, Yi-Jun |
|---|---|
| 論文名稱: |
應用模式樹探討沼氣發電效率的影響因子 Applying model trees to explore the influencing factors of biogas power generation efficiency |
| 指導教授: |
翁慈宗
Wong, Tzu-Tsung |
| 學位類別: |
碩士 Master |
| 系所名稱: |
管理學院 - 工業與資訊管理學系碩士在職專班 Department of Industrial and Information Management (on the job class) |
| 論文出版年: | 2021 |
| 畢業學年度: | 109 |
| 語文別: | 中文 |
| 論文頁數: | 51 |
| 中文關鍵詞: | 沼氣發電 、線性迴歸 、模式樹 、數值預測 |
| 外文關鍵詞: | biogas power generation, linear regression, model tree, numerical prediction |
| 相關次數: | 點閱:88 下載:0 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
由於人類對化石燃料的依賴,現今使用的大部分能源皆來自於化石資源,而化石資源的過度使用,已造成地球能源缺乏以及造成對環境的負面影響日益嚴重,因此,再生能源成為各國發展重點。在台灣,畜牧業佔農業產值極高的比例,各畜牧場飼養的牲畜所產生的廢水量驚人,成為台灣第三大污染源。隨著環保意識抬高,以及再生能源發展沿革,政府開始輔導畜牧場設置沼氣發電系統,以達到廢水處理以及能源再利用之效益,而有限能源的再利用率也成為相關研究重點。本研究收集國內某畜牧場沼氣發電系統的歷史監控數據,由於製程屬於非批量性生產,故分為全製程、發電機前、發電機後搭配不同時間區間進行屬性組合的資料整理,採用複迴歸模型進行各組屬性組合間的共線性分析,進行製程屬性的篩選;接著用篩選後的資料來建立模式樹。透過模型建立結果,由相關係數、相對絕對誤差與相對方根誤差進行模型的篩選,由發電機後感測器的組合採6小時為時間區間所建構的模型為最佳,經過分析以發電機運轉時間、逆變器3電量的感測器統計特徵對於發電量的預測為重要的影響因子。而全製程感測器組合則是採3小時為區間所建立的模型為次佳,其分析結果以環境溫度、原水入料量、發電機作動次數的感測器統計特徵對於發電量為較重要的影響因子;其次為逆變器電表。本研究結果可有效的提供發電量提升的優化方向,並可來作為系統監測的依據或將來類似系統建置的參考,進而提升發電的品質。
The excessive use of fossil resources has an increasingly serious negative impact on the environment. With the rising awareness of environmental protection, all countries pay their attention on the evolution of renewable energy. The Taiwan government encourages livestock farms to install biogas power generation systems for the benefits of wastewater treatment and energy reuse. This research collects historical data of a livestock farm biogas power generation system to determine the critical factors for the amount of power generation. Since the system is continuous, three processes with two different time intervals for aggregating the data collected from sensors are analyzed to find the best one for our study. Collinearity analysis is used to remove unnecessary attributes. The one that has the smallest prediction error is the process for the power generator in which data are aggregated in six-hour interval. The model tree for the best process has 11 leaf nodes, and the critical factors filtered from the tree are the operating time and the current flow of the third inverter. The same technique is also applied on the second best process which includes all sensors to identify additional critical attributes. The critical attributes found in this study can provide an applicable direction for increasing the amount of power generation.
【英文文獻】
Ambuchi, J. J., Liu, J. F., Wang, H. M., Shan, L. L., Zhou, X. T., Mohammed, M. O. A., & Feng, Y. J. (2016). Microbial community structural analysis of an expanded granular sludge bed (EGSB) reactor for beet sugar industrial wastewater (BSIW) treatment. Applied Microbiology and Biotechnology, 100(10), 4651-4661.
Cohen, p., West,S. G., & Aiken,L. S. (2014). Applied Multiple Regression/ Correlation Analysis for the Behavioral Sciences.(3rd ed), Lawrence Erlbaum Associates Publishers.
Hamdi, M., & Taieb, A. (2017). Numerical prediction of methane- and biogas-fuelled power generation. 5th International Conference on Renewable Energy, 29,33-38
IEA (2017)。World Energy Outlook 2017.(1st ed), Paris
IPCC (2014). Climate Change 2014: Synthesis Report. (1st), IPCC, Geneva, Switzerland.
IPCC (2013). Climate Change 2013: The Physical Science Basis. (1st), Cambridge University Press, Cambridge.
Jung, S. Y., & Park, J. (2017). Numerical prediction of effects of CO2 or H2 content on combustion characteristics and generation efficiency of biogas-fueled engine generator. International Journal of Hydrogen Energy, 42(27), 16991-16999.
Kayaalp, F. & Başarslan, M. S. (2018). Open source data mining programs: a case study on R. Düzce University Journal of Science and Technology, 6, 455-468.
Yadav, V. K., Ray, A., & Ravi, M. R. (2019). Experimental and computational investigation of the laminar burning velocity of hydrogen-enriched biogas. Fuel, 235, 810-821.
Mason,C. H. & Perreault Jr,W. D.(1991). Collinearity, power, and interpretation of multiple regression analysis. Journal of Marketing Research,39(1),84-97.
Nonaka, H. O. B., & Pereira, F. M. (2016). Experimental and numerical study of CO2 content effects on the laminar burning velocity of biogas. Fuel, 182, 382-390.
Tan, P. N., Steinbach, M., Karpatne A. & Kumar, V. (2006). Introduction to Data Mining (1st). Minnesota, Pearson.
Sahota, S., Shah, G., Ghosh, P., Kapoor, R., Sengupta, S., Singh, P., Vijay, V., Sahay, A., Vijay, V. K. & Thakur, I. S. (2018). Review of trends in biogas upgradation technologies and future perspectives. Bioresource Technology Reports, 1, 79-88.
Saranya, C., & Manikandan, G. (2013). A study on normalization techniques for privacy preserving. International Journal of Engineering and Technology, 5(3), 2701-2704.
Singhal, S., Agarwal, S., Arora, S., Sharma, P., & Singhal, N. (2017). Upgrading techniques for transformation of biogas to bio-CNG: a review. International Journal of Energy Research, 41(12), 1657-1669.
Vasavan, A., de Goey, P., & van Oijen, J. (2018). Numerical study on the autoignition of biogas in moderate or intense low oxygen dilution nonpremixed combustion systems. Energy & Fuels, 32(8), 8768-8780.
Vondra, M., Tous, M., & Teng, S. Y. (2019). Digestate evaporation treatment in biogas plants: A techno-economic assessment by Monte Carlo, neural networks and decision trees. Journal of Cleaner Production, 238, 26.
Witten, I. H., Frank, E. & Hall, M. A. (2011). Data Mining: Practical Machine Learning Tools and Techniques (3rd ed.). Cambridge, Morgan Kaufmann.
【中文文獻】
行政院經濟部(2017),能源發展綱領,台北市,行政院經濟部。
行政院農委會(2019)。綠色國民所得帳農業固體廢棄物。Retrieved from https://agrstat.coa.gov.tw/sdweb/public/common/Download.aspx
李宗翰(2015),「提高豬場沼氣發電效益之研究」,國立交通大學交通大學機械工程系研究所博士論文。
李韋柔(2016),「特徵選取前處理於填補遺漏值之影響」,國立中央大學資訊管理學系研究所博士論文。
呂家華、李翰林、胡耀祖、陳惠萍、郭軒甫、楊秉純(2020),能源轉型白皮書,行政院經濟部能源局。
林君宜(2015),「運用M5'模式樹分析放款發生逾期因子」,國立成功大學高階管理碩士在職專班(EMBA)碩士論文。
林威丞(2015),「養豬場沼氣曝氣水洗脫硫之研究」,國立嘉義大學生物機電工程學系研究所碩士論文。
涂有為(2011),「固體停留時間對高溫厭氧消化甲烷產出影響之研究」,國立中央大學環境工程研究所在職專班碩士論文。
徐瑋勵(2016),「沼氣發電對溫室氣體的減量及排放與環境衝擊之評估」,國立臺灣大學環境工程學研究所碩士論文。
徐英綺、李志杰、蔡宗原、林依杏、洪宗良(2018),沼氣發電系統最佳化技術與實例說明,取自http://www.tbva.org.tw/archive/report/F45.pdf
陳偉禎(2017),「探討以皮革浸灰削肉廢棄物和稻稈調整碳氮比對厭氧共消化的影響」,國立臺灣大學臺灣大學動物科學技術學研究所碩士論文。
鄭少斐(2013),「以資料探勘法探索可轉換生質能之微生物」,國立成功大學成功大學機械工程學系研究所博士論文。
蕭士斌(2015),「以厭氧消化程序處理養豬廢水效能評估之研究」,國立中興大學中興大學土木工程學系所碩士論文。
蕭庭訓(2020),「畜牧場沼氣利用」,科學發展,第565期,頁22-27。
校內:2026-07-25公開