查詢結果分析
相關文獻
- 智慧型自動化匝道儀控系統之研究
- 線切割放電加工故障診斷專家系統之研發
- 輸入特徵信號對類神經網路診斷系統之鑑別影響
- 構建高速公路入口匝道儀控專家系統之研究
- 人類錯誤診斷之即時資訊輔助研究
- A Study of Power Transformer Fault Diagnosis Using Neural Network
- 智慧型設備維護診斷方法探討
- A Study of the Application of Artificial Neural Networks in the Expert System of Sheet Bending Design
- 建立專家系統並利用類神經網路學習金屬焊接條件之最佳參數
- 人工智慧在紡紗工程上的發展和應用
頁籤選單縮合
題名 | 智慧型自動化匝道儀控系統之研究=Developing Intelligent Freeway Ramp Metering Control Systems |
---|---|
作者 | 魏健宏; 吳耿毓; Wei, Chien-hung; Wu, Kun-yu; |
期刊 | 國家科學委員會研究彙刊. 人文及社會科學 |
出版日期 | 19970700 |
卷期 | 7:3 1997.07[民86.07] |
頁次 | 頁371-389 |
分類號 | 557.311 |
語文 | chi |
關鍵詞 | 儀控率; 類神經網路; 自我修正; 專家系統; 匝道儀控; Pamp metering control; Expert system; Neural network; Metering rate; Self-adjustment; |
中文摘要 | 現今所發展之高速公路最佳化儀控率模式,皆以複雜的數學運算來求解。本研究嘗 試利用人工智慧取代目前的方式,將整個高速公路系統視為一個生命體,以具有時空特性之類 神經網路學習控制策略並做出反射動作,輔以自我修正專家系統判斷行為的偏誤與決定修正 方向,使整個高速公路系統具有感覺、反應與試誤性學習的能力。當系統運作時,類神經網路 推估儀控率並據以實施,實施後由自我修正模組評估儀控之績效,擬定修正策略,回饋到類神 經網路模組中,做線上回饋訓練。經由觀察匝道儀控系統運作與分析各項績效指標,發現類 神經網路系統確實能夠記取歷次錯誤之經驗,藉以修正其行為,並逐漸適應環境,朝著所設定 的目標日漸改善。 |
英文摘要 | Artificial intelligence, instead of arithmetic methods, is used to provide the optimal freeway ramp metering control strategy. We treat the freeway as a biological system which can learn control strategies and make suitable decisions. An expert system is developed to evaluate the decisions and to suggest adjusting directions. First, a neural network metering rate estimating model is constructed with time-space feature for handling dynamic freeway traffic flow, Second, a metering rate self-adjustment expert system is formed for modifying Inappropriate metering rates. Then, relevant information is sent back to the neural network metering rate estimating model for on-line retraining. From the simulation results, it is found that the neural network system is able to adjust control strategies toward preset targets and the overall performance is gradually improved. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。