State-of-Charge Estimation for Electric Scooters by Using Learning Mechanisms

This paper presents a state of charge (SOC) learning system designed to improve the performance of current methods of measuring SOC in electric scooters or electric vehicles. The SOC, or residual capacity of an electric vehicle battery, is difficult to determine because of the battery’s nonlinear discharge characteristics. The proposed learning system uses learning controllers, fuzzy neural networks, and cerebellar model articulation controller (CMAC) networks for estimating and predicting the nonlinear characteristics of the battery’s energy consumption. In addition to estimating the availability or residual battery power, the learning system could also provide addition information, such as an estimated traveling distance and the maximum allowable safe speed.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/00189545
• Authors:
  • Lee, Der-Tsai
  • Shiah, Shaw-Ji
  • Lee, Chien-Ming
  • Wang, Ying-Chung
• Publication Date: 2007-3

Language

• English

Media Info

• Media Type: Print
• Features: Figures; References;
• Pagination: pp 544-556
• Serial:
  • IEEE Transactions on Vehicular Technology
  • Volume: 56
  • Issue Number: 2
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 0018-9545
  • Serial URL: http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=25

Subject/Index Terms

• TRT Terms: Electric batteries; Electric vehicles; Fuzzy algorithms; Machine learning; Mathematical models; Scooters; Speed
• Subject Areas: Energy; Highways; Vehicles and Equipment; I91: Vehicle Design and Safety;

Filing Info

• Accession Number: 01044917
• Record Type: Publication
• Source Agency: UC Berkeley Transportation Library
• Files: BTRIS, TRIS
• Created Date: Mar 28 2007 2:41PM