English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 55025/89277 (62%)
造訪人次 : 10606139      線上人數 : 25
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    請使用永久網址來引用或連結此文件: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/108195

    題名: Intelligent exponential sliding-mode control with uncertainty estimator for antilock braking systems
    作者: Hsu, Chun-Fei
    關鍵詞: Antilock braking system (ABS);Intelligent sliding-mode control;Exponential reaching;law;Fuzzy neural network;Functional neural network
    日期: 2016-08-01
    上傳時間: 2016-11-08 02:10:25 (UTC+8)
    出版者: Springer U K
    摘要: The purpose of the antilock braking system (ABS) is to regulate the wheel longitudinal slip at its optimum point in order to generate the maximum braking force; however, the vehicle braking dynamic is highly nonlinear. To relax the requirement of detailed system dynamics, this paper proposes an intelligent exponential sliding-mode control (IESMC) system for an ABS. A functional recurrent fuzzy neural network (FRFNN) uncertainty estimator is designed to approximate the unknown nonlinear term of ABS dynamics, and the parameter adaptation laws are derived in the sense of projection algorithm and Lyapunov stability theorem to ensure the stable control performance. Since the outputs of the functional expansion unit are used as the output weights of the FRFNN uncertainty estimator, the FRFNN can effectively capture the input–output dynamic mapping. In addition, a nonlinear reaching law, which contains an exponential term of sliding surface to smoothly adapt the variations of sliding surface, is designed to reduce the level of the chattering phenomenon. Finally, the simulation results demonstrate that the proposed IESMC system can achieve robustness slip tracking performance in different road conditions.
    關聯: Neural Computing and Applications 27(6) pp.1463-1475
    DOI: 10.1007/s00521-015-1946-4
    顯示於類別:[電機工程學系暨研究所] 期刊論文


    檔案 描述 大小格式瀏覽次數



    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回饋