KMITL

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

Browse

Settings

Author: search.filters.author.Rattanakun, KritsanaHas files: No

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    2D-CNN Based Classification on Water Leakage Identification in Automatic Pump
    (2026-01-01)
    Satthamsakul, Sutham
    ;
    Rattanakun, Kritsana
    ;
    Khummongkol, Rojanee
    ;
    Tangsrirat, Worapong
    This study proposes an approach for classification of unusual in automatic water pump systems, especially on a water leakage, one of the key issues that can significantly affect system efficiency and cause serious damage. The method utilizes motor current signals, which are transformed into 2D spectrograms using the Short-Time Fourier Transform (STFT). These spectrograms are then classified by a 2D Convolutional Neural Network (2D-CNN) Designed to determine between usual and unusual operating conditions with high accuracy. Experimental results indicate that the model can effectively detect unusual and leakage events when trained with appropriate parameters, such as a learning rate of 0.001 and 60 training epochs. This model serves as an efficient tool for preventing system failures and reducing maintenance costs in automatic water pump systems.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    FINITE-TIME NONLINEAR SPEED CONTROLLER OF PERMANENT MAGNET SYNCHRONOUS MOTOR USING C MEX S-FUNCTION
    (2025-07-31)
    Cholahan, Varin
    ;
    Rattanakun, Kritsana
    ;
    Tangsrirat, Worapong
    Permanent magnet synchronous motor (PMSM) has high torque and possesses a simple structure relative to its capacity. It has been popularly applied in numerous industrial applications. Nonetheless, PMSM is sensitive to both internal and external disturbances. It exhibits significant nonlinearity and functions as a multi-variable coupling system. Therefore, a control system capable of delivering superior performance must be nonlinear. Owing to its considerable robustness capability, the sliding-mode control (SMC) technique is extensively utilized in this research. This work also demonstrates the use of C Mex S-function, the most efficient code-oriented tool, to simulate the operation of nonlinear systems. The C-Mex S-function is an effective and practical approach for developing models within the SIMULINK/MATLAB user interface environment and utilizing its requisite capabilities. Consequently, the nonlinear controller established in this study is carried out via the C-Mex S-function. Let’s manipulate the characteristics of the PMSM to converge to equilibrium within a finite time period. The tracking speed signal can be quickly followed with a high robustness against disturbances, uncertainties, and unmodeled variables. In addition, the Lyapunov function is employed to assess the stability of the developed SMC controllers, whereby the stable convergence property is demonstrated and proven. To illustrate the performance of the continuous fast-terminal sliding-mode control scheme, some simulation tests are performed on the speed regulation of the PMSM drive plant. The simulations are presented as code resembling the C programming language within SIMULINK/MATLAB. The findings show that the proposed controller achieves a speed overshoot of less than 3%, a settling time of approximately 0.15 seconds, and a steady-state error of less than 0.5 rad/s under a load torque of 1.5 Nm. These results highlight the high performance and robustness of the proposed speed controller.