KMITL

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

Browse

Settings

Author: search.filters.author.Kittiratsatcha, SupatSubject: search.filters.subject.Battery

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    ACCURATE STATE OF CHARGE ESTIMATION OF LITHIUM-ION BATTERY USING RECURRENT AND NON-RECURRENT NEURAL NETWORKS FOR WLTP DRIVING PROFILES
    (2024-12-01)
    Praisan, Akkarawat
    ;
    Polmai, Sompob
    ;
    Kittiratsatcha, Supat
    Estimating the state of charge (SoC) of a battery is essential to maximize its performance and ensure reliable operation and battery life. Nowadays, many countries are increasingly adopting electric vehicles (EVs) with lithium-ion batteries due to their high specific energy and long service life. This paper presents a method for estimating the state of charge of lithium-ion batteries using artificial neural networks, specifically the Feedforward Neural Network (FNN) and Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM), through a data-driven approach. The training and testing of the networks are conducted using recorded datasets of the battery, based on the WLTP driving profiles class 2 and class 3. These driving profiles are specifically designed for testing electric vehicles, thereby enhancing the realism of the state of charge estimation by the network. In terms of the analytical aspect, the FNN was able to train the network faster due to its simpler structure, requiring less computation. On the other hand, the LSTM demonstrated more accurate SoC estimation with fewer response oscillations, thanks to its ability to learn and adapt network parameters internally.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A number of RC pairs consideration of electrical equivalent circuit model of li-ion battery
    (2020-07-01)
    Kamrueng, Chairat
    ;
    Kittiratsatcha, Supat
    ;
    Polmai, Sompob
    In 20th century, handheld electronic appliances have changed our live style and make things as comfortable as never had before. Of course, the main important part of those devices is the battery. Li-ion battery is the most used not only in those small appliances such as smart phone, tablet, laptop, etc., but also in high power application like in electric vehicle or backup system for power grid. To fully utilize the battery for those applications, a suitable electrical equivalent circuit model must be selected for precise estimation of battery voltage and remaining capacity. Thevenin-based equivalent circuit model with various number of RC pairs has been used in many literatures which give different accuracy of voltages results. This paper proposed the consideration for number of RC pairs for equivalent circuit model using curve fitting method and the goodness of fit results base on the values of root mean square error at several state of charge of battery. The results show good indicator between simple circuit model with low accuracy or complex circuit model with higher accuracy.