- 期刊
以隱藏式馬可夫鏈分析並模擬風速資料
Developement of a Hidden Markov Chain Model for Analyzing and Simulating Wind Speed Data
摘要
在作風能評估、結構耐風設計或節能設計時，建立合適的風速模型來模擬是一個很重要的研究課題；此模型應可模擬產生與實測風速統計特性類似之人造風速資料。本文嘗試以隱藏式馬可夫鏈(Hidden Markov Chain；HMC)模型，配合常態轉換法，分析實測風速，並產生人造風速。與前人所採用之模型不同的是，此模型是個非穩態(non-stationary)模型，因此可以適當呈現實際風速資料中的非穩態現象；同時我們也發展了新的演算法。為了驗證所提模型與方法之適用性與準確性，本文以無劇烈氣候變化測站之風速為例，模擬產生人造風速資料；模擬結果顯示人造風速與實測風速有相似之統計特性。
並列摘要
Field wind data is essential for wind resistant structural design or for wind energy evaluation. However, field wind data is often quite limited; therefore, generating synthetic wind data whose statistical properties are similar to those from observed wind data is a critical research topic. This research proposes a Hidden Markov Chain (HMC) model to analyze field wind data and to simulate synthetic wind data. Compared to the models adopted by previous research, the chosen model is different in the way that it is a non-stationary model. Moreover, new algorithms are developed in this paper to simulate synthetic wind data based on the HMC model and field wind data. The recorded wind speed data is used to demonstrate the implementation of the proposed approach. It is shown that the statistical properties of the simulated data are very similar to those of the field data.
延伸閱讀
- 傅偉翔（2020）。風速資料的時間序列模型分析〔碩士論文，國立政治大學〕。華藝線上圖書館。https://doi.org/10.6814/NCCU202001702
- Tso, B., Tso, H. K., & Olsen, R. C. (2006). 植基於隱匿式馬可夫模式之多頻譜、多視角影像判釋. 航測及遙測學刊, 11(1), 13-26. https://doi.org/10.6574/JPRS.2006.11(1).2
- 施文富（2007）。基於漸進式隱藏馬可夫模型與Windows系統呼叫之可調適性異常入侵偵測方法〔碩士論文，國立中央大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0031-0207200917345047
- 黃任德（2011）。利用隱馬可夫模型於偵測網域快速轉換機制下之策略〔碩士論文，國立暨南國際大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0020-2908201107230300
- Fung, S. L. (2006). High-dimensional Markov chain models for categorical data sequences with applications [doctoral dissertation, The University of Hong Kong]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0029-1812201200013935