KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Has files: NoSubject: search.filters.subject.artificial neural network (ANN)

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    An HSC/battery energy storage system-based regenerative braking system control mechanism for battery electric vehicles
    (2019-03-01)
    Kiddee, Kunagone
    ;
    Keyoonwong, Wiwat
    ;
    Khan-Ngern, Werachet
    This paper proposes a novel hybrid energy storage system (HESS) for the regenerative braking system (RBS) of the front-wheel induction motor-driven battery electric vehicle. The HESS is an amalgamation of multiple hybrid supercapacitors (HSCs) and lithium-ion battery cells. An artificial neural network (ANN)-based RBS control mechanism was used to optimize the switching scheme of the RBS's three-phase inverter and the vehicular breaking force distribution. In the regenerative braking mode, the ANN-based HSC/battery RBS transferred the braking energy to be stored in the HSC and, upon reaching the HSC's maximum safety threshold, then to the battery. In addition, the RBS control mechanism could achieve uniform braking force distribution between the front and rear wheels of the vehicle. Furthermore, our findings revealed that the experimental HSC/battery RBS program enhanced the harvesting of the regenerative braking energy, as was evident from the longer driving distance vis-à-vis that of the battery-only vehicle. The HSC/battery RBS also contributed to improved vehicle acceleration and an extended battery life. © 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Microwave sensor for tangerine classification based on coupled-patch antennas
    (2016-08-02)
    Leekul, Prapan
    ;
    Chivapreecha, Sorawat
    ;
    Krairiksh, Monai
    This paper deals with a microwave sensor for classifying tangerines by flavour using coupled-patch antennas. The operating frequency of the antennas is 2.45 GHz. The sensor determines the flavour of each tangerine by measuring the magnitudes of coupled signals of the antennas with the tangerine fruit at the centre. The sorting is carried out using an artificial neural network implemented on a field programmable gate array. The classification performance of the sensor is 95% accurate, so it has potential for use in sorting tangerines by flavour. In addition, the system uncertainty is analysed to determine optimal operating conditions.